System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting, by a sensor, biological information when a user speaks; means for sending the collected biological information to a server; means for analyzing, by the server, the collected biological information by using a generation AI, and determining a speaking improvement point; means for generating, by the server, specific advice and an ideal speaking sample based on the improvement point; and means for providing, by a device, the advice and the ideal speaking sample sent by the server to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional voice training requires instruction by a professional trainer, which is problematic in terms of both time and money. It is also difficult to obtain objective feedback based on scientific data. Therefore, there is a need for an effective and scientific voice training method that many people can use on a daily basis. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system described in the claims. Specifically, a sensor collects biometric information when the user speaks, and the device sends this information to a server. The server uses generative AI to analyze the biometric information and identify areas for vocal improvement. The server then generates specific advice and ideal vocal samples based on the areas for improvement, and the device provides these to the user. This allows users to receive effective voice training based on scientific data, regardless of time or location.

[0006] A "sensor" is a device that collects biometric information, specifically breathing patterns, voice frequencies, and muscle movements, when a user speaks.

[0007] "Biometric information" refers to data related to the user's vocal activity, including breathing patterns, voice frequencies, muscle movements, and the like.

[0008] A "terminal" is a device used by a user, and is equipped with means for transmitting biometric information collected from a sensor to a server.

[0009] The "server" is a computer system that analyzes the received biometric information and uses generative AI to identify areas for vocal improvement and generate advice and samples of ideal vocalizations.

[0010] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate results tailored to specific purposes.

[0011] "Advice" refers to methods for improving or training vocalization that the server provides to the user based on the results of analysis of biometric information.

[0012] The "ideal speech sample" is a speech sample of the speech that the user should aim for, created by the server using a generation AI.

[0013] "Areas for improvement in vocalization" refers to the problems with vocalization and areas that need improvement that the generating AI points out as a result of analyzing biometric information. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system for scientifically and easily conducting voice training, and utilizes sensors, terminals, servers, and generation AI.

[0036] System Overview

[0037] 1. The user launches the application

[0038] The user launches a voice training application on a device such as a smartphone or tablet.

[0039] When the application is launched, the system begins arming the sensors.

[0040] 2. Sensor data collection

[0041] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[0042] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[0043] 3. Data transmission

[0044] The terminal transmits the collected biometric information to the server.

[0045] In this case, the terminal has a means for transmitting data to a server via a network such as the Internet.

[0046] 4. AI-based data analysis

[0047] Based on the data received by the server, the data is analyzed using generative AI.

[0048] The AI ​​identifies vocal problems (for example, inconsistencies in pitch) and areas for improvement (for example, practice to stabilize pitch).

[0049] 5. Generate feedback

[0050] The server generates feedback based on the results of the AI ​​analysis.

[0051] The feedback includes specific advice and examples of ideal utterances, which are created by generative AI.

[0052] 6. Providing Feedback

[0053] The terminal provides the user with the feedback sent from the server.

[0054] Through the application interface, users can view the feedback (advice and samples of ideal pronunciation).

[0055] Specific examples

[0056] 1. Launching the application

[0057] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor."

[0058] 2. Sensor data collection

[0059] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[0060] 3. Data transmission

[0061] The collected sensor data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes detailed information about the user's breathing patterns, voice frequency, and muscle movements.

[0062] 4. AI-based data analysis

[0063] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for vocal improvement. For example, it identifies specific practice methods for stabilizing pitch.

[0064] 5. Generate feedback

[0065] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample speech of ideal pronunciation created by the AI, allowing the user to understand specifically what points need improvement.

[0066] 6. Providing Feedback

[0067] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and check detailed advice and sample voices of ideal pronunciation. The user can then use this information to carry out daily voice training.

[0068] The above is a detailed description of the embodiment of the present invention. This system enables users to perform effective voice training based on scientific data, regardless of time or place.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] A user launches an application on a smartphone or tablet.

[0072] The user taps to open the voice training app on their device.

[0073] When the application is launched, a message will appear indicating that the sensor is ready.

[0074] Step 2:

[0075] The device initializes the sensor.

[0076] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[0077] A device initialization message will appear letting the user know that it is ready.

[0078] Step 3:

[0079] The user selects training mode and begins speaking.

[0080] The user selects "Start Training" from the application menu.

[0081] Follow the instructions in the application and speak in front of the microphone.

[0082] Step 4:

[0083] The device collects sensor data.

[0084] The device collects real-time data such as the user's breathing patterns, voice frequency, and muscle movements.

[0085] The collected data is temporarily stored in memory.

[0086] Step 5:

[0087] The terminal transmits the collected data to the server.

[0088] The collected biometric information is organized and sent to a server via the Internet.

[0089] Display a notification that data transmission is complete.

[0090] Step 6:

[0091] The server receives the data and analyzes it using the generating AI.

[0092] The server receives the transmitted data and prepares it for analysis.

[0093] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[0094] Step 7:

[0095] The server generates the feedback.

[0096] The server generates specific advice in text format based on the analysis results.

[0097] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[0098] Step 8:

[0099] The device provides feedback to the user.

[0100] The terminal displays the feedback received from the server to the user.

[0101] Within the application interface, users can view advice and samples of ideal pronunciation.

[0102] This explains the specific processing flow of the program and the detailed operation at each step.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] Conventional voice training requires specialized knowledge and equipment, making it difficult for average users to easily practice based on scientific data. It is also difficult to objectively evaluate one's own vocal performance and find effective ways to improve it. To solve this problem, voice training must be something that users can do regardless of time or place, and that training must be based on scientific data.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes a means for analyzing the received biometric information using a generative AI model and identifying areas for vocal improvement, a means for generating specific advice and an ideal vocal sample based on the areas for improvement, and a means for the generated ideal vocal sample to be a voice sample created by the generative AI model, thereby enabling users to receive accurate and effective vocal training based on scientific data without being bound by time or place.

[0108] A "sensor" is a device for collecting biometric information when a user speaks.

[0109] A "terminal" is a device operated by a user, which temporarily stores collected data and has the function of transmitting the data to a server.

[0110] "Server" means a computer system that receives data transmitted from a terminal via a network and generates analysis and feedback using a generative AI model.

[0111] The "generative AI model" is an artificial intelligence algorithm that analyzes problems and areas for improvement in vocalization based on collected biometric information and generates ideal vocalization samples.

[0112] "Biometric information" refers to data such as the user's breathing pattern, voice frequency, and muscle movements when speaking.

[0113] A "prompt sentence" is an instruction sentence that prompts the user to make a specific utterance, and is provided as a guideline during training.

[0114] "Feedback" is specific advice and ideal vocalization samples generated by the server based on the results of analysis using a generative AI model.

[0115] "Device" is a general term for data collection equipment such as sensors and terminals operated by users.

[0116] "Network" refers to the overall communications infrastructure for sending and receiving data, including the Internet and local area networks.

[0117] "Data integration" is the process of combining multiple biometric data sets collected from sensors into a single data set.

[0118] The "HTTPS protocol" is an encrypted communication protocol for securely sending and receiving data over the Internet.

[0119] The present invention is a system for scientifically and easily conducting voice training, which utilizes sensors, terminals, a server, and a generative AI model.

[0120] The system is configured as follows:

[0121] Sensor: A device that collects biometric information (breathing patterns, voice frequency, muscle movements) when the user speaks.

[0122] Terminal: A device operated by the user, such as a smartphone or tablet, that temporarily stores data from sensors and transmits it to a server as needed.

[0123] Server: A computer system that receives data sent from the device and uses a generative AI model to analyze the data and generate feedback.

[0124] Generative AI model: An artificial intelligence algorithm that analyzes speech problems and areas for improvement based on collected biometric information, and generates ideal speech samples.

[0125] System Overview

[0126] Launching the application

[0127] The user launches the voice training application on a device such as a smartphone or tablet. After launching, the application begins preparing the sensor and instructs the user to perform the pairing process.

[0128] Sensor data collection

[0129] The user selects training mode and begins speaking as instructed by the application. The sensors collect breathing patterns, voice frequencies, and muscle movements in real time and temporarily store them in the device's memory.

[0130] Sending data

[0131] The terminal packages the collected biometric data and sends it to a server over the network using the HTTPS protocol, encrypting the data.

[0132] AI-powered data analysis

[0133] The server inputs the received data into a generative AI model, which analyzes pitch variations and irregular breathing patterns to identify areas for improvement and problems with vocalization. For example, the AI ​​uses machine learning libraries such as TENSORFLOW (registered trademark).

[0134] Generate feedback

[0135] The server generates feedback based on the analysis results, including specific areas for improvement and sample speech for ideal pronunciation. The generative AI model generates the speech samples.

[0136] Providing Feedback

[0137] The terminal displays the feedback sent from the server to the user, who can then review the feedback through the application interface and use it to improve their training.

[0138] Specific examples

[0139] Prompt Sentence Examples

[0140] "Say the following clearly and loudly: a-e-i-o"

[0141] After this instruction, the user starts recording and the sensors collect data.

[0142] This system allows users to easily perform effective voice training based on scientific data anywhere.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1:

[0145] Launching the application

[0146] The user launches a voice training application on a device such as a smartphone or tablet.

[0147] The device will launch the application and display the home screen. When launched for the first time, it will display a message indicating pairing with the sensor device.

[0148] Input: User taps to launch the app

[0149] Output: Home screen display, sensor preparation instructions

[0150] Step 2:

[0151] Sensor data collection

[0152] The user selects training mode and begins speaking as instructed by the application, such as prompting them to "Say the following clearly and loudly: a-e-i-o."

[0153] Sensors capture breathing patterns, voice frequencies, and muscle movements in real time to capture this data.

[0154] The terminal integrates the data received from the sensors and temporarily stores it in memory.

[0155] Input: User's speech data

[0156] Output: Sensor data stored on the device

[0157] Step 3:

[0158] Sending data

[0159] The device packages the collected biometric information and sends it over the network to a server, encrypting the data using the HTTPS protocol.

[0160] The server stores the received data in a database and returns a reception confirmation response to the terminal.

[0161] Input: Sensor data stored on the device

[0162] Output: Data sent to the server, acknowledgement response

[0163] Step 4:

[0164] AI-powered data analysis

[0165] The server inputs the received data into a generative AI model.

[0166] Generative AI models analyze pitch variations and breathing irregularities to identify areas for improvement and problems with vocalization. This analysis is performed using machine learning libraries such as TensorFlow.

[0167] The server stores the AI ​​analysis results in a database.

[0168] Input: Sensor data sent to the server

[0169] Output: Analysis results

[0170] Step 5:

[0171] Generate feedback

[0172] The server uses a generative AI model to generate feedback for the user based on the analysis results, including specific areas for improvement and audio samples of ideal pronunciation.

[0173] A generative AI model generates sample audio of ideal utterances.

[0174] The server packages the generated feedback and sample audio and prepares it for transmission to the user's device.

[0175] Input: Analysis results

[0176] Output: Feedback data and sample audio

[0177] Step 6:

[0178] Providing Feedback

[0179] The terminal receives the feedback data sent from the server and displays it to the user.

[0180] The user checks the feedback content (specific advice and sample audio of ideal pronunciation) through the application interface.

[0181] Input: Feedback data sent from the server

[0182] Output: Feedback display to the user

[0183] The above is the specific flow of processing by this system.

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Conventional autonomous vehicles do not provide accurate and timely driving assistance based on user voice commands, so it is necessary to improve the user experience and the quality of safe driving.In addition, there is a lack of systems that can analyze the user's spoken voice and provide appropriate feedback, so a consistent solution that combines both is required.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes: means for collecting biometric information from a sensor when the user speaks; means for transmitting the collected biometric information to the server; means for the server to analyze the collected biometric information using a generation AI and identify areas for improvement in the user's speech; means for the server to generate specific advice and ideal speech samples based on the areas for improvement; means for the terminal to provide the user with the advice and ideal speech samples transmitted from the server; means for collecting the user's voice in the vehicle and analyzing driving instructions and speech data; and means for providing optimal voice instructions while driving based on the analyzed data. This enables consistent provision of accurate and timely driving assistance based on the user's voice instructions and feedback on speech.

[0189] A "sensor" is a device for collecting biometric information when a user speaks.

[0190] "Biometric information" is data obtained from the user's body, such as breathing patterns, voice frequencies, and muscle movements.

[0191] A "terminal" is an electronic device such as a smartphone or tablet operated by a user, or an in-vehicle information system.

[0192] The "server" is an information processing device that receives collected biometric information and analyzes the data using the generation AI.

[0193] "Generative AI" is an artificial intelligence technology that analyzes collected biometric information, identifies areas for improvement in the user's vocalization, and generates samples of ideal vocalizations.

[0194] "Advice" is specific instructions or suggestions provided to the user for improvements to the speech identified by the generative AI.

[0195] An "ideal speech sample" is a speech sample created by generative AI that users should emulate.

[0196] "In-vehicle voice collection means" means a means for collecting a user's voice in real time using microphones or other sensors installed in an autonomous vehicle.

[0197] "Driving instructions" are voice guides related to driving provided to the user, such as route guidance to the destination and operation instructions while driving.

[0198] "Voice instruction optimization" means analyzing the user's voice data and providing driving instructions with optimal timing and content based on that information.

[0199] The present invention provides a system for analyzing voice instructions from a user of an autonomous vehicle and providing accurate and timely driving assistance and feedback regarding speech. Specific embodiments for carrying out the present invention are described below.

[0200] System Overview

[0201] 1. Sensor Preparation

[0202] Microphones and other necessary sensors will be placed inside the autonomous vehicle to prepare for collecting biometric information when the user speaks.

[0203] 2. Collection of audio data

[0204] When the user gives a voice command, the microphone and sensors collect the voice in real time.

[0205] The data collected includes biometric information such as breathing patterns, voice frequencies, and muscle movements.

[0206] 3. Data transmission

[0207] The terminal temporarily stores the collected data and transmits it to a server via the Internet.

[0208] 4. Data Analysis

[0209] The server analyzes the received data using a generative AI model (e.g., GPT-4 (registered trademark)). It analyzes pitch fluctuations, duration fluctuations, breathing irregularities, etc. in the speech and identifies areas for improvement in the speech.

[0210] 5. Generate feedback

[0211] Based on the analysis results, the server generates feedback to provide to the user, including specific advice and sample audio of ideal pronunciation created by the generation AI.

[0212] 6. Providing Feedback

[0213] The terminal receives the feedback sent from the server and provides it to the user through a display or audio device in the vehicle.

[0214] System configuration and operation

[0215] This system consists of the following hardware and software:

[0216] Hardware

[0217] Microphone: Installed inside the vehicle to collect the user's voice.

[0218] Sensors: Detect breathing patterns, voice frequencies, and muscle movements.

[0219] On-board computer (Edge Computing Device): Temporarily stores collected data and sends it to a server.

[0220] Display and audio devices: Provide feedback to the user.

[0221] software

[0222] Generative AI models (e.g., GPT-4): Analyze voice data and generate feedback.

[0223] Data collection and transmission software framework (e.g., TensorFlow, PyTorch): Responsible for data preprocessing and transmission.

[0224] Database for real-time data processing (e.g., Firebase, AWS (registered trademark) DynamoDB): Stores and manages data.

[0225] Program processing and specific examples

[0226] Below is a concrete example of how the system works.

[0227] 1. Collection and Analysis

[0228] When a user gives a voice command such as "Turn left at the next traffic light," microphones and sensors collect voice data and associated biometric information.

[0229] 2. Data transmission and analysis

[0230] The collected data is sent from the onboard computer to a server where it is analyzed by a generative AI model.

[0231] The analysis results in the generation of feedback regarding voice command optimization and pronunciation (e.g., "Your pitch is unstable; please speak more slowly next time").

[0232] 3. Providing Feedback

[0233] The onboard computer receives the analysis results and provides feedback to the user via a display and audio device.

[0234] Prompt Sentence Examples

[0235] User says: Turn left at the next light.

[0236] Task: Analyze the user's pronunciation and speech patterns and suggest improvements to voice guidance, especially optimizing instructions to the next traffic light.

[0237] Example output: "Turn left at the next traffic light. Then go straight for 500 meters."

[0238] This allows users to receive accurate and timely driving assistance while also receiving feedback on areas for improvement in their speech, enabling an overall safer and more comfortable driving experience.

[0239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0240] Step 1:

[0241] The user issues a voice command. The input is the user's voice data, which is collected by microphones and sensors in the car. The collected data includes breathing patterns, voice frequency, and biometric information such as muscle movements.

[0242] Step 2:

[0243] The terminal temporarily stores the collected biometric information and performs data preprocessing. The input is biometric information, which is converted to a format for transmission to the server. The output is formatted biometric information.

[0244] Step 3:

[0245] The terminal transmits the formatted biometric information to the server via the Internet. At this stage, the input is the formatted biometric information, and the output is a transmission success message to the server.

[0246] Step 4:

[0247] The server analyzes the received data using a generative AI model (e.g., GPT-4). The input is the collected biometric information, and data calculations identify areas for optimizing voice instructions and improving speech production. The output is the analysis results.

[0248] Step 5:

[0249] The server generates feedback based on the analysis results. The input is the analysis results, and the generative AI model is used to generate specific advice and sample audio of ideal pronunciation. The output is feedback data.

[0250] Step 6:

[0251] The server sends the generated feedback data to the terminal. The input is the feedback data, and the output is a transmission success message to the terminal.

[0252] Step 7:

[0253] The terminal receives the feedback data sent from the server and provides it to the user through the in-car display or audio device. The input is the feedback data, and the output is specific advice and audio samples that are displayed or played to the user.

[0254] This allows the user to receive accurate and timely driving assistance based on voice instructions, while also receiving feedback on areas for improvement in their speech.

[0255] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0256] The present invention relates to a voice training system that utilizes sensors, terminals, servers, generative AI, and an emotion engine, and realizes more personalized training by recognizing not only the user's biometric information when speaking, but also the user's emotions and providing feedback.

[0257] System Overview

[0258] 1. The user launches the application

[0259] The user launches the voice training app on their smartphone or tablet. When the app launches, a message appears indicating that the sensors and emotion engine are ready.

[0260] 2. Sensor data collection

[0261] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[0262] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[0263] 3. Collecting Emotional Data

[0264] The emotion engine installed in the device recognizes the user's emotions based on their voice and biometric information.

[0265] Recognized emotion data is also stored on the device in real time.

[0266] 4. Data transmission

[0267] The device transmits the collected biometric information and emotion data to the server.

[0268] The transmitted data includes detailed information about the user's breathing patterns, voice frequencies, muscle movements, and perceived emotions.

[0269] 5. AI-based data analysis

[0270] Based on the data received by the server, the data is analyzed using generative AI.

[0271] The AI ​​analyzes pitch fluctuations, vocal duration, and breathing timing to identify areas for vocal improvement, and also takes emotional data into account to tailor feedback.

[0272] 6. Generate feedback

[0273] The server generates specific advice in text format based on the analysis results, and the advice content is adjusted based on the user's emotions as recognized by the emotion engine.

[0274] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[0275] 7. Providing Feedback

[0276] The terminal provides the feedback received from the server to the user.

[0277] Through the application interface, users can view feedback (advice and ideal vocalization samples), and personalized advice is provided based on emotions recognized by the emotion engine.

[0278] Specific examples

[0279] 1. Launching the application

[0280] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine."

[0281] 2. Sensor data collection

[0282] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[0283] 3. Collecting Emotional Data

[0284] While speaking, the emotion engine analyzes the user's voice and biometric information to recognize the user's emotions in real time. Emotional data is also stored on the device and integrated with other biometric information.

[0285] 4. Data transmission

[0286] The collected biometric and emotional data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes details on the user's breathing patterns, voice frequency, muscle movements, and recognized emotions.

[0287] 5. AI-based data analysis

[0288] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for improvement in the voice. At the same time, it also analyzes emotions recognized by the emotion engine to personalize the feedback.

[0289] 6. Generate feedback

[0290] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample audio of ideal speech created by the generation AI. It also includes personalized advice based on the user's emotions recognized by the emotion engine, allowing the user to understand appropriate areas for improvement based on their own emotional state.

[0291] 7. Providing Feedback

[0292] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and review detailed advice and sample audio of ideal speech. Additionally, personalized advice is provided based on the user's emotions as recognized by the emotion engine.

[0293] This invention allows users to receive scientifically and individually optimized voice training that was previously unavailable. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The user launches an application.

[0297] Users simply tap to launch the voice training app on their smartphone or tablet.

[0298] When the application launches, it displays the message "Preparing sensors and emotion engine."

[0299] Step 2:

[0300] The device initializes the sensor.

[0301] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[0302] A device initialization message will appear letting the user know that it is ready.

[0303] Step 3:

[0304] The device will initialize the emotion engine.

[0305] The emotion engine is activated and ready to analyze the user's voice and biometric information in real time.

[0306] Once initialization is complete, a completion message will be displayed on the terminal.

[0307] Step 4:

[0308] The user selects training mode and begins speaking.

[0309] The user selects "Start Training" from the application menu.

[0310] Follow the instructions in the application and speak in front of the microphone.

[0311] Step 5:

[0312] The device collects sensor data and emotion data.

[0313] The device collects biometric information such as the user's breathing patterns, voice frequency, and muscle movements in real time.

[0314] The collected data is temporarily stored in memory.

[0315] At the same time, the emotion engine analyzes the user's voice and biometric information to collect emotional data.

[0316] Step 6:

[0317] The terminal transmits the collected data to the server.

[0318] The collected biometric and emotional data is organized and sent to a server via the Internet.

[0319] A notification that data transmission is complete is displayed to the user.

[0320] Step 7:

[0321] The server receives the data and analyzes it using the generating AI.

[0322] The server prepares the received data for analysis.

[0323] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[0324] The emotional data recognized by the emotion engine is also analyzed to personalize the feedback content.

[0325] Step 8:

[0326] The server generates the feedback.

[0327] The server generates specific advice in text format based on the analysis results.

[0328] Generative AI is used to create sample audio of ideal pronunciation.

[0329] The advice content is adjusted according to the emotions recognized by the emotion engine, and feedback is generated that takes into consideration the user's psychological state.

[0330] Step 9:

[0331] The device provides feedback to the user.

[0332] The terminal displays the feedback received from the server to the user.

[0333] The application interface provides users with detailed advice and ideal vocalization samples, and also provides personalized advice based on emotions recognized by the emotion engine.

[0334] The above is a flow of specific processing steps for carrying out the invention based on the claims.

[0335] Example 2

[0336] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] Conventional voice training systems provide feedback based solely on the user's vocal data and are unable to provide personalized advice that takes into account the user's emotional state. This limits the effectiveness of training. The present invention aims to enable more personalized training by recognizing not only the user's biometric information but also their emotional state and incorporating this information into the feedback.

[0338] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting biometric information when the user speaks using a sensor; means for recognizing emotional data when the user speaks using the sensor; means for transmitting the collected biometric information and emotional data to the server; means for analyzing the collected biometric information and emotional data using a generative AI model and identifying areas for improvement in the speech; means for generating specific advice and ideal speech samples based on the analysis results; and means for providing the advice and ideal speech samples transmitted from the server to the user on the terminal. This enables personalized training that takes the user's emotional state into consideration.

[0339] ---

[0340] A "sensor" is a device that collects biometric information and emotional data when a user speaks.

[0341] The "server" is an entity that analyzes the collected biometric information and emotional data, generates feedback, and sends it to the terminal.

[0342] A "generative AI model" is an algorithm that analyzes collected data, identifies areas for improvement in vocalization, and generates specific advice and samples of ideal vocalizations.

[0343] "Biometric information" refers to breathing patterns, voice frequencies and muscle movements acquired when the user speaks.

[0344] "Emotion data" is data that indicates the emotional state of the user that can be inferred from the tone of the user's voice and biological information.

[0345] A "terminal" is a device used by a user that receives and displays feedback provided by a server.

[0346] "Advice" refers to specific instructions or suggestions that the generative AI model gives to the user to improve their speech based on the analysis results.

[0347] "Ideal speech samples" refer to the best speech examples created by the generative AI model for users to refer to.

[0348] ---

[0349] This invention relates to a voice training system that utilizes sensors, terminals, a server, a generative AI model, and an emotion engine. The system aims to realize more personalized training by recognizing not only the user's biometric information when speaking but also the user's emotions and providing feedback.

[0350] System Overview

[0351] 1. Launching the application

[0352] A user launches a voice training app on their smartphone or tablet. When the application is launched, the device begins the initialization process for the sensors and emotion engine. The message displayed is "Preparing sensors and emotion engine."

[0353] 2. Sensor data collection

[0354] When a user selects training mode and starts speaking, sensors collect biometric information from the user. For example, a microphone captures the voice, a breathing pattern sensor measures the rhythm and depth of breathing, and an electromyography sensor detects muscle movement. The device integrates this data and stores it in memory in real time.

[0355] 3. Collecting Emotional Data

[0356] The device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state, and the recognized emotional data is also stored on the device in real time.

[0357] 4. Data transmission

[0358] The device transmits the collected biometric and emotional data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[0359] 5. AI-based data analysis

[0360] Based on the data received by the server, a detailed analysis is performed using a generative AI model. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account and adjusts the feedback content. Specifically, the AI ​​analyzes the data and returns the analysis results to the server.

[0361] 6. Generate feedback

[0362] The server generates feedback to provide to the user based on the analysis results. The generative AI model generates sample speech of ideal pronunciation along with specific advice. The content of the advice is also adjusted based on the emotional data recognized by the emotion engine.

[0363] 7. Providing Feedback

[0364] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[0365] The specific hardware, software, and generative AI models used

[0366] Hardware:

[0367] Microphone: Used to capture audio data.

[0368] Breathing pattern sensor: Measures the rhythm and depth of the user's breathing.

[0369] Myoelectric sensor: Detects muscle movement.

[0370] Smartphone or tablet: A device on which the application runs.

[0371] software:

[0372] Voice training application: Interacts with the user.

[0373] Emotion engine: Recognizes emotions by analyzing the user's tone of voice and biometric information.

[0374] Server software: Uses generative AI models to analyze data and generate feedback.

[0375] Examples of concrete examples and prompts

[0376] Specific examples

[0377] The user taps the voice training app on their smartphone's home screen to launch it. The first time the app is launched, pairing with the sensor device is required. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine." When the user selects training mode and begins speaking, the sensor collects breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory. While speaking, the emotion engine analyzes the user's voice and biometric information to recognize their emotions in real time. This data is sent from the device to the server. The server uses a generative AI to analyze the received data, identifying pitch variations, duration fluctuations, breathing irregularities, and other factors to identify areas for improvement in the voice. It also analyzes emotion data and personalizes the feedback. Based on the analysis results, the server generates feedback to provide to the user and creates a sample voice of the ideal voice. The device receives the feedback sent from the server and presents it to the user on the app interface. The user then reviews detailed advice and sample voices of the ideal voice, and receives personalized advice based on the emotion data.

[0378] Prompt Sentence Examples

[0379] "How do I launch the Voice Training app on my smartphone and complete the sensor pairing?"

[0380] "While making the speech, explain how the sensor collects the data."

[0381] "Please explain in detail how the emotion engine recognizes and collects the user's emotions while speaking."

[0382] The above is a description of the mode for carrying out the invention. This allows users to receive scientifically and individually optimized voice training that was not possible with conventional methods. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[0383] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0384] Step 1:

[0385] The user launches the application

[0386] A user launches a voice training app on their smartphone or tablet. When the app launches, the device begins the initialization process for the sensors and emotion engine.

[0387] Input: Tap the app icon

[0388] Output: The sensor and emotion engine initialization is complete and the message "Preparing the sensor and emotion engine" is displayed to the user.

[0389] Step 2:

[0390] Sensor data collection

[0391] When a user selects training mode and starts speaking, sensors collect biometric information from the user's speech, including breathing patterns, voice frequency, and muscle movements. The device integrates this data and stores it in memory in real time.

[0392] Input: User's speech data

[0393] Output: Breathing patterns, voice frequency, and muscle movement data are stored in the device's memory.

[0394] Step 3:

[0395] Collecting Emotional Data

[0396] While speaking, the device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state. The recognized emotional data is also stored in memory in real time.

[0397] Input: User's voice tone, biometric information

[0398] Output: The user's emotion data is stored in the device's memory.

[0399] Step 4:

[0400] Sending data

[0401] The device transmits the collected biometric and emotional data to the server using a secure communication protocol (HTTPS).

[0402] Input: User breathing patterns, voice frequency, muscle movements, emotional data

[0403] Output: Data is sent to the server.

[0404] Step 5:

[0405] AI-powered data analysis

[0406] The server then uses a generative AI model to perform a detailed analysis of the received data. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account to personalize the feedback.

[0407] Input: collected biometric information, emotional data

[0408] Output: Analysis results and feedback

[0409] Step 6:

[0410] Generate feedback

[0411] The server generates feedback to provide to the user based on the analysis results, uses a generative AI model to generate sample speech of ideal utterances, and adjusts the content of advice based on the user's emotions recognized by the emotion engine.

[0412] Input: Analysis results

[0413] Output: Specific advice and sample audio of ideal pronunciation

[0414] Step 7:

[0415] Providing Feedback

[0416] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[0417] Input: Feedback sent by the server

[0418] Output: Display feedback to the user

[0419] The above is the processing flow of the program for this system. By including the input and output at each step and the specific operations, the operation of the entire system becomes clear.

[0420] (Application example 2)

[0421] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0422] Conventional voice training systems are limited in their effectiveness because they rely only on feedback based on the user's biometric information and are unable to consider the user's emotional state. Furthermore, there is a lack of systems that provide real-time feedback on performance in virtual worlds, making it difficult for users to improve immediately.

[0423] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting collected biometric information and emotional data to the server, means for analyzing the collected biometric information and emotional data using a generation AI and identifying areas for improvement in vocalization, and means for generating specific advice and ideal vocalization samples based on the areas for improvement. This provides personalized feedback that takes the user's emotional state into consideration, enabling effective real-time improvements in performance in the virtual world.

[0424] A "sensor" is a device for collecting biometric information when a user speaks.

[0425] "Biometric information" is data such as a user's breathing patterns, voice frequency, and muscle movements.

[0426] "Emotion data" is data obtained by analyzing the user's emotional state.

[0427] The "server" is a computer system that analyzes the collected biometric and emotional data and generates feedback.

[0428] "Generative AI" is a type of artificial intelligence that uses collected data to generate vocal improvements and ideal vocal samples.

[0429] "Analysis" refers to the process of using collected biometric and emotional data to identify areas for vocal improvement.

[0430] "Advice" refers to specific instructions for improvement provided to the user.

[0431] An "ideal speech sample" is a voice sample of the desired speech that users should aim for, created by generative AI.

[0432] "Terminal" means a device used by a user that receives and displays feedback sent from the server.

[0433] A "virtual world" is an imaginary environment or space generated by a computer system.

[0434] "Real-time feedback" refers to feedback that is provided immediately in response to a user's actions.

[0435] This invention relates to a voice training system that uses sensors, terminals, servers, generative AI, and emotional data. It recognizes the user's biometric information and emotional state when speaking, and provides personalized feedback based on that information, thereby enabling more effective training and real-time feedback in a virtual world.

[0436] System configuration

[0437] The system consists of the following hardware and software:

[0438] Sensor: A device that collects a user's breathing patterns, voice frequencies, and muscle movements

[0439] Device: The device used by the user, such as a smartphone or tablet.

[0440] Server: A computer system that analyzes collected biometric and emotional data and generates feedback.

[0441] Generative AI: Artificial intelligence that generates vocal improvements and ideal vocal samples

[0442] Emotion Engine: A software module that analyzes the user's emotional state

[0443] Implementation details

[0444] 1. User launches application:

[0445] The user launches the voice training app on their device. Pairing with the sensor device is required. When the app is launched for the first time, a message confirming connection to the sensor device is displayed.

[0446] 2. Biometric and emotional data collection:

[0447] Sensors collect the user's breathing patterns, voice frequency, and muscle movements in real time, while an emotion engine analyzes the user's voice and biometric data to recognize the user's emotional state. This data is temporarily stored on the device.

[0448] 3. Data transmission to the server:

[0449] The collected biometric and emotional data is sent from the device to a server, which then prepares the data for analysis.

[0450] 4. Data Analysis:

[0451] The server uses generative AI to analyze biometric and emotional data to identify areas for improvement in the user's vocalizations and adjusts the feedback content to take into account the perceived emotional state.

[0452] 5. Feedback Generation:

[0453] Based on the analysis results, the server generates specific advice and ideal speech samples. The generated feedback is provided in a personalized format, taking into account the user's emotional state.

[0454] 6. Providing Feedback:

[0455] The device receives the feedback sent from the server and displays it to the user, who can then play back and check detailed advice and sample voices of ideal pronunciation. Real-time feedback is also provided during performance in the virtual world.

[0456] Specific examples

[0457] For example, when a singer performs on a virtual stage, sensors capture their voice frequency and breathing patterns, and the emotion engine recognizes the user's level of tension. This data is sent to a server, and the AI ​​generates feedback such as "Your pitch is too high. Relax a bit and stabilize your pitch," and provides this feedback to the user in real time via their device.

[0458] Example of an input prompt for a generative AI model:

[0459] Prompt: Generate specific feedback to provide to the user based on the following biometric and audio data:

[0460] Biometric information: breathing pattern = [0.7], muscle movement = [1.3]

[0461] Audio data: frequency=[250 Hz], volume=[1.0]

[0462] Emotion: [Tension]

[0463] Feedback statement:

[0464] "Your pitch is too high. Relax a bit and stabilize your pitch. Try taking deep breaths and relaxing techniques."

[0465] This allows users to instantly improve their vocal technique and perform better in virtual environments.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] The user launches the application. The user launches the voice training app on their device and pairs it with the sensor device. A connection confirmation message is displayed the first time the app is launched. The input data is the user's operation information, and the output data is the connection status with the sensor device.

[0469] Step 2:

[0470] The sensor collects biometric information when the user speaks. The sensor captures the user's breathing pattern, voice frequency, and muscle movement in real time. The collected data is temporarily stored on the device. The input data is the user's biometric information, and the output data is the collected biometric information.

[0471] Step 3:

[0472] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the collected biometric information and voice data to recognize the user's emotional state. The analysis results are saved on the device. The input data is biometric information and voice data, and the output data is emotion data.

[0473] Step 4:

[0474] The device sends the collected biometric information and emotional data to the server. The device sends the temporarily stored data to the server. The server receives these data. The input data is the biometric information and emotional data, and the output data is the data sent to the server.

[0475] Step 5:

[0476] The server analyzes the data using a generation AI. The generation AI analyzes biometric and emotional data to identify areas for improvement in the user's speech. At the same time, it takes the emotional data into account and adjusts the feedback content. The input data are biometric and emotional data, and the output data are areas for improvement and the adjusted feedback content.

[0477] Step 6:

[0478] The server generates specific advice and ideal speech samples. Using a generation AI, it generates specific advice and ideal speech sample audio to provide to the user. The input data are areas for improvement and feedback, and the output data are specific advice and ideal speech samples.

[0479] Step 7:

[0480] The terminal provides the generated feedback to the user. The terminal receives the advice and voice sample sent from the server and displays them to the user. The user can play and check the detailed advice and ideal voice sample voice. The input data is the feedback from the server, and the output data is the feedback display to the user.

[0481] Step 8:

[0482] It provides real-time feedback in the virtual world. Data is collected and analyzed again in real time during performance, and immediate feedback is given. This allows users to immediately identify areas for improvement and improve their performance. The input data is biometric and emotional data during performance, and the output data is real-time feedback.

[0483] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0484] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0485] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0486] [Second embodiment]

[0487] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0488] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0489] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0490] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0491] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0492] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0493] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0494] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0495] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0496] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0497] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0498] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0499] This invention is a system for scientifically and easily conducting voice training, and utilizes sensors, terminals, servers, and generation AI.

[0500] System Overview

[0501] 1. The user launches the application

[0502] The user launches a voice training application on a device such as a smartphone or tablet.

[0503] When the application is launched, the system begins arming the sensors.

[0504] 2. Sensor data collection

[0505] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[0506] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[0507] 3. Data transmission

[0508] The terminal transmits the collected biometric information to the server.

[0509] In this case, the terminal has a means for transmitting data to a server via a network such as the Internet.

[0510] 4. AI-based data analysis

[0511] Based on the data received by the server, the data is analyzed using generative AI.

[0512] The AI ​​identifies vocal problems (for example, inconsistencies in pitch) and areas for improvement (for example, practice to stabilize pitch).

[0513] 5. Generate feedback

[0514] The server generates feedback based on the results of the AI ​​analysis.

[0515] The feedback includes specific advice and examples of ideal utterances, which are created by generative AI.

[0516] 6. Providing Feedback

[0517] The terminal provides the user with the feedback sent from the server.

[0518] Through the application interface, users can view the feedback (advice and samples of ideal pronunciation).

[0519] Specific examples

[0520] 1. Launching the application

[0521] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor."

[0522] 2. Sensor data collection

[0523] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[0524] 3. Data transmission

[0525] The collected sensor data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes detailed information about the user's breathing patterns, voice frequency, and muscle movements.

[0526] 4. AI-based data analysis

[0527] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for vocal improvement. For example, it identifies specific practice methods for stabilizing pitch.

[0528] 5. Generate feedback

[0529] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample speech of ideal pronunciation created by the AI, allowing the user to understand specifically what points need improvement.

[0530] 6. Providing Feedback

[0531] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and check detailed advice and sample voices of ideal pronunciation. The user can then use this information to carry out daily voice training.

[0532] The above is a detailed description of the embodiment of the present invention. This system enables users to perform effective voice training based on scientific data, regardless of time or place.

[0533] The processing flow will be explained below.

[0534] Step 1:

[0535] A user launches an application on a smartphone or tablet.

[0536] The user taps to open the voice training app on their device.

[0537] When the application is launched, a message will appear indicating that the sensor is ready.

[0538] Step 2:

[0539] The device initializes the sensor.

[0540] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[0541] A device initialization message will appear letting the user know that it is ready.

[0542] Step 3:

[0543] The user selects training mode and begins speaking.

[0544] The user selects "Start Training" from the application menu.

[0545] Follow the instructions in the application and speak in front of the microphone.

[0546] Step 4:

[0547] The device collects sensor data.

[0548] The device collects real-time data such as the user's breathing patterns, voice frequency, and muscle movements.

[0549] The collected data is temporarily stored in memory.

[0550] Step 5:

[0551] The terminal transmits the collected data to the server.

[0552] The collected biometric information is organized and sent to a server via the Internet.

[0553] Display a notification that data transmission is complete.

[0554] Step 6:

[0555] The server receives the data and analyzes it using the generating AI.

[0556] The server receives the transmitted data and prepares it for analysis.

[0557] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[0558] Step 7:

[0559] The server generates the feedback.

[0560] The server generates specific advice in text format based on the analysis results.

[0561] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[0562] Step 8:

[0563] The device provides feedback to the user.

[0564] The terminal displays the feedback received from the server to the user.

[0565] Within the application interface, users can view advice and samples of ideal pronunciation.

[0566] This explains the specific processing flow of the program and the detailed operation at each step.

[0567] Example 1

[0568] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0569] Conventional voice training requires specialized knowledge and equipment, making it difficult for average users to easily practice based on scientific data. It is also difficult to objectively evaluate one's own vocal performance and find effective ways to improve it. To solve this problem, voice training must be something that users can do regardless of time or place, and that training must be based on scientific data.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0571] In this invention, the server includes a means for analyzing the received biometric information using a generative AI model and identifying areas for vocal improvement, a means for generating specific advice and an ideal vocal sample based on the areas for improvement, and a means for the generated ideal vocal sample to be a voice sample created by the generative AI model, thereby enabling users to receive accurate and effective vocal training based on scientific data without being bound by time or place.

[0572] A "sensor" is a device for collecting biometric information when a user speaks.

[0573] A "terminal" is a device operated by a user, which temporarily stores collected data and has the function of transmitting the data to a server.

[0574] "Server" means a computer system that receives data transmitted from a terminal via a network and generates analysis and feedback using a generative AI model.

[0575] The "generative AI model" is an artificial intelligence algorithm that analyzes problems and areas for improvement in vocalization based on collected biometric information and generates ideal vocalization samples.

[0576] "Biometric information" refers to data such as the user's breathing pattern, voice frequency, and muscle movements when speaking.

[0577] A "prompt sentence" is an instruction sentence that prompts the user to make a specific utterance, and is provided as a guideline during training.

[0578] "Feedback" is specific advice and ideal vocalization samples generated by the server based on the results of analysis using a generative AI model.

[0579] "Device" is a general term for data collection equipment such as sensors and terminals operated by users.

[0580] "Network" refers to the overall communications infrastructure for sending and receiving data, including the Internet and local area networks.

[0581] "Data integration" is the process of combining multiple biometric data sets collected from sensors into a single data set.

[0582] The "HTTPS protocol" is an encrypted communication protocol for securely sending and receiving data over the Internet.

[0583] The present invention is a system for scientifically and easily conducting voice training, which utilizes sensors, terminals, a server, and a generative AI model.

[0584] The system is configured as follows:

[0585] Sensor: A device that collects biometric information (breathing patterns, voice frequency, muscle movements) when the user speaks.

[0586] Terminal: A device operated by the user, such as a smartphone or tablet, that temporarily stores data from sensors and transmits it to a server as needed.

[0587] Server: A computer system that receives data sent from the device and uses a generative AI model to analyze the data and generate feedback.

[0588] Generative AI model: An artificial intelligence algorithm that analyzes speech problems and areas for improvement based on collected biometric information, and generates ideal speech samples.

[0589] System Overview

[0590] Launching the application

[0591] The user launches the voice training application on a device such as a smartphone or tablet. After launching, the application begins preparing the sensor and instructs the user to perform the pairing process.

[0592] Sensor data collection

[0593] The user selects training mode and begins speaking as instructed by the application. The sensors collect breathing patterns, voice frequencies, and muscle movements in real time and temporarily store them in the device's memory.

[0594] Sending data

[0595] The terminal packages the collected biometric data and sends it to a server over the network using the HTTPS protocol, encrypting the data.

[0596] AI-powered data analysis

[0597] The server inputs the received data into a generative AI model, which analyzes pitch variations and irregular breathing patterns to identify areas for improvement and problems with vocalization. For example, the AI ​​uses machine learning libraries such as TensorFlow.

[0598] Generate feedback

[0599] The server generates feedback based on the analysis results, including specific areas for improvement and sample speech for ideal pronunciation. The generative AI model generates the speech samples.

[0600] Providing Feedback

[0601] The terminal displays the feedback sent from the server to the user, who can then review the feedback through the application interface and use it to improve their training.

[0602] Specific examples

[0603] Prompt Sentence Examples

[0604] "Say the following clearly and loudly: a-e-i-o"

[0605] After this instruction, the user starts recording and the sensors collect data.

[0606] This system allows users to easily perform effective voice training based on scientific data anywhere.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Step 1:

[0609] Launching the application

[0610] The user launches a voice training application on a device such as a smartphone or tablet.

[0611] The device will launch the application and display the home screen. When launched for the first time, it will display a message indicating pairing with the sensor device.

[0612] Input: User taps to launch the app

[0613] Output: Home screen display, sensor preparation instructions

[0614] Step 2:

[0615] Sensor data collection

[0616] The user selects training mode and begins speaking as instructed by the application, such as prompting them to "Say the following clearly and loudly: a-e-i-o."

[0617] Sensors capture breathing patterns, voice frequencies, and muscle movements in real time to capture this data.

[0618] The terminal integrates the data received from the sensors and temporarily stores it in memory.

[0619] Input: User's speech data

[0620] Output: Sensor data stored on the device

[0621] Step 3:

[0622] Sending data

[0623] The device packages the collected biometric information and sends it over the network to a server, encrypting the data using the HTTPS protocol.

[0624] The server stores the received data in a database and returns a reception confirmation response to the terminal.

[0625] Input: Sensor data stored on the device

[0626] Output: Data sent to the server, acknowledgement response

[0627] Step 4:

[0628] AI-powered data analysis

[0629] The server inputs the received data into a generative AI model.

[0630] Generative AI models analyze pitch variations and breathing irregularities to identify areas for improvement and problems with vocalization. This analysis is performed using machine learning libraries such as TensorFlow.

[0631] The server stores the AI ​​analysis results in a database.

[0632] Input: Sensor data sent to the server

[0633] Output: Analysis results

[0634] Step 5:

[0635] Generate feedback

[0636] The server uses a generative AI model to generate feedback for the user based on the analysis results, including specific areas for improvement and audio samples of ideal pronunciation.

[0637] A generative AI model generates sample audio of ideal utterances.

[0638] The server packages the generated feedback and sample audio and prepares it for transmission to the user's device.

[0639] Input: Analysis results

[0640] Output: Feedback data and sample audio

[0641] Step 6:

[0642] Providing Feedback

[0643] The terminal receives the feedback data sent from the server and displays it to the user.

[0644] The user checks the feedback content (specific advice and sample audio of ideal pronunciation) through the application interface.

[0645] Input: Feedback data sent from the server

[0646] Output: Feedback display to the user

[0647] The above is the specific flow of processing by this system.

[0648] (Application example 1)

[0649] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0650] Conventional autonomous vehicles do not provide accurate and timely driving assistance based on user voice commands, so it is necessary to improve the user experience and the quality of safe driving.In addition, there is a lack of systems that can analyze the user's spoken voice and provide appropriate feedback, so a consistent solution that combines both is required.

[0651] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0652] In this invention, the server includes: means for collecting biometric information from a sensor when the user speaks; means for transmitting the collected biometric information to the server; means for the server to analyze the collected biometric information using a generation AI and identify areas for improvement in the user's speech; means for the server to generate specific advice and ideal speech samples based on the areas for improvement; means for the terminal to provide the user with the advice and ideal speech samples transmitted from the server; means for collecting the user's voice in the vehicle and analyzing driving instructions and speech data; and means for providing optimal voice instructions while driving based on the analyzed data. This enables consistent provision of accurate and timely driving assistance based on the user's voice instructions and feedback on speech.

[0653] A "sensor" is a device for collecting biometric information when a user speaks.

[0654] "Biometric information" is data obtained from the user's body, such as breathing patterns, voice frequencies, and muscle movements.

[0655] A "terminal" is an electronic device such as a smartphone or tablet operated by a user, or an in-vehicle information system.

[0656] The "server" is an information processing device that receives collected biometric information and analyzes the data using the generation AI.

[0657] "Generative AI" is an artificial intelligence technology that analyzes collected biometric information, identifies areas for improvement in the user's vocalization, and generates samples of ideal vocalizations.

[0658] "Advice" is specific instructions or suggestions provided to the user for improvements to the speech identified by the generative AI.

[0659] An "ideal speech sample" is a speech sample created by generative AI that users should emulate.

[0660] "In-vehicle voice collection means" means a means for collecting a user's voice in real time using microphones or other sensors installed in an autonomous vehicle.

[0661] "Driving instructions" are voice guides related to driving provided to the user, such as route guidance to the destination and operation instructions while driving.

[0662] "Voice instruction optimization" means analyzing the user's voice data and providing driving instructions with optimal timing and content based on that information.

[0663] The present invention provides a system for analyzing voice instructions from a user of an autonomous vehicle and providing accurate and timely driving assistance and feedback regarding speech. Specific embodiments for carrying out the present invention are described below.

[0664] System Overview

[0665] 1. Sensor Preparation

[0666] Microphones and other necessary sensors will be placed inside the autonomous vehicle to prepare for collecting biometric information when the user speaks.

[0667] 2. Collection of audio data

[0668] When the user gives a voice command, the microphone and sensors collect the voice in real time.

[0669] The data collected includes biometric information such as breathing patterns, voice frequencies, and muscle movements.

[0670] 3. Data transmission

[0671] The terminal temporarily stores the collected data and transmits it to a server via the Internet.

[0672] 4. Data Analysis

[0673] The server analyzes the received data using a generative AI model (e.g., GPT-4), analyzing pitch fluctuations, duration variations, and breathing irregularities in the speech to identify areas for improvement in the voice.

[0674] 5. Generate feedback

[0675] Based on the analysis results, the server generates feedback to provide to the user, including specific advice and sample audio of ideal pronunciation created by the generation AI.

[0676] 6. Providing Feedback

[0677] The terminal receives the feedback sent from the server and provides it to the user through a display or audio device in the vehicle.

[0678] System configuration and operation

[0679] This system consists of the following hardware and software:

[0680] Hardware

[0681] Microphone: Installed inside the vehicle to collect the user's voice.

[0682] Sensors: Detect breathing patterns, voice frequencies, and muscle movements.

[0683] On-board computer (Edge Computing Device): Temporarily stores collected data and sends it to a server.

[0684] Display and audio devices: Provide feedback to the user.

[0685] software

[0686] Generative AI models (e.g., GPT-4): Analyze voice data and generate feedback.

[0687] Data collection and transmission software framework (e.g., TensorFlow, PyTorch): Responsible for data preprocessing and transmission.

[0688] Databases for real-time data processing (e.g., Firebase, AWS DynamoDB): Store and manage data.

[0689] Program processing and specific examples

[0690] Below is a concrete example of how the system works.

[0691] 1. Collection and Analysis

[0692] When a user gives a voice command such as "Turn left at the next traffic light," microphones and sensors collect voice data and associated biometric information.

[0693] 2. Data transmission and analysis

[0694] The collected data is sent from the onboard computer to a server where it is analyzed by a generative AI model.

[0695] The analysis results in the generation of feedback regarding voice command optimization and pronunciation (e.g., "Your pitch is unstable; please speak more slowly next time").

[0696] 3. Providing Feedback

[0697] The onboard computer receives the analysis results and provides feedback to the user via a display and audio device.

[0698] Prompt Sentence Examples

[0699] User says: Turn left at the next light.

[0700] Task: Analyze the user's pronunciation and speech patterns and suggest improvements to voice guidance, especially optimizing instructions to the next traffic light.

[0701] Example output: "Turn left at the next traffic light. Then go straight for 500 meters."

[0702] This allows users to receive accurate and timely driving assistance while also receiving feedback on areas for improvement in their speech, enabling an overall safer and more comfortable driving experience.

[0703] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0704] Step 1:

[0705] The user issues a voice command. The input is the user's voice data, which is collected by microphones and sensors in the car. The collected data includes breathing patterns, voice frequency, and biometric information such as muscle movements.

[0706] Step 2:

[0707] The terminal temporarily stores the collected biometric information and performs data preprocessing. The input is biometric information, which is converted to a format for transmission to the server. The output is formatted biometric information.

[0708] Step 3:

[0709] The terminal transmits the formatted biometric information to the server via the Internet. At this stage, the input is the formatted biometric information, and the output is a transmission success message to the server.

[0710] Step 4:

[0711] The server analyzes the received data using a generative AI model (e.g., GPT-4). The input is the collected biometric information, and data calculations identify areas for optimizing voice instructions and improving speech production. The output is the analysis results.

[0712] Step 5:

[0713] The server generates feedback based on the analysis results. The input is the analysis results, and the generative AI model is used to generate specific advice and sample audio of ideal pronunciation. The output is feedback data.

[0714] Step 6:

[0715] The server sends the generated feedback data to the terminal. The input is the feedback data, and the output is a transmission success message to the terminal.

[0716] Step 7:

[0717] The terminal receives the feedback data sent from the server and provides it to the user through the in-car display or audio device. The input is the feedback data, and the output is specific advice and audio samples that are displayed or played to the user.

[0718] This allows the user to receive accurate and timely driving assistance based on voice instructions, while also receiving feedback on areas for improvement in their speech.

[0719] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0720] The present invention relates to a voice training system that utilizes sensors, terminals, servers, generative AI, and an emotion engine, and realizes more personalized training by recognizing not only the user's biometric information when speaking, but also the user's emotions and providing feedback.

[0721] System Overview

[0722] 1. The user launches the application

[0723] The user launches the voice training app on their smartphone or tablet. When the app launches, a message appears indicating that the sensors and emotion engine are ready.

[0724] 2. Sensor data collection

[0725] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[0726] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[0727] 3. Collecting Emotional Data

[0728] The emotion engine installed in the device recognizes the user's emotions based on their voice and biometric information.

[0729] Recognized emotion data is also stored on the device in real time.

[0730] 4. Data transmission

[0731] The device transmits the collected biometric information and emotion data to the server.

[0732] The transmitted data includes detailed information about the user's breathing patterns, voice frequencies, muscle movements, and perceived emotions.

[0733] 5. AI-based data analysis

[0734] Based on the data received by the server, the data is analyzed using generative AI.

[0735] The AI ​​analyzes pitch fluctuations, vocal duration, and breathing timing to identify areas for vocal improvement, and also takes emotional data into account to tailor feedback.

[0736] 6. Generate feedback

[0737] The server generates specific advice in text format based on the analysis results, and the advice content is adjusted based on the user's emotions as recognized by the emotion engine.

[0738] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[0739] 7. Providing Feedback

[0740] The terminal provides the feedback received from the server to the user.

[0741] Through the application interface, users can view feedback (advice and ideal vocalization samples), and personalized advice is provided based on emotions recognized by the emotion engine.

[0742] Specific examples

[0743] 1. Launching the application

[0744] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine."

[0745] 2. Sensor data collection

[0746] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[0747] 3. Collecting Emotional Data

[0748] While speaking, the emotion engine analyzes the user's voice and biometric information to recognize the user's emotions in real time. Emotional data is also stored on the device and integrated with other biometric information.

[0749] 4. Data transmission

[0750] The collected biometric and emotional data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes details on the user's breathing patterns, voice frequency, muscle movements, and recognized emotions.

[0751] 5. AI-based data analysis

[0752] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for improvement in the voice. At the same time, it also analyzes emotions recognized by the emotion engine to personalize the feedback.

[0753] 6. Generate feedback

[0754] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample audio of ideal speech created by the generation AI. It also includes personalized advice based on the user's emotions recognized by the emotion engine, allowing the user to understand appropriate areas for improvement based on their own emotional state.

[0755] 7. Providing Feedback

[0756] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and review detailed advice and sample audio of ideal speech. Additionally, personalized advice is provided based on the user's emotions as recognized by the emotion engine.

[0757] This invention allows users to receive scientifically and individually optimized voice training that was previously unavailable. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] The user launches an application.

[0761] Users simply tap to launch the voice training app on their smartphone or tablet.

[0762] When the application launches, it displays the message "Preparing sensors and emotion engine."

[0763] Step 2:

[0764] The device initializes the sensor.

[0765] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[0766] A device initialization message will appear letting the user know that it is ready.

[0767] Step 3:

[0768] The device will initialize the emotion engine.

[0769] The emotion engine is activated and ready to analyze the user's voice and biometric information in real time.

[0770] Once initialization is complete, a completion message will be displayed on the terminal.

[0771] Step 4:

[0772] The user selects training mode and begins speaking.

[0773] The user selects "Start Training" from the application menu.

[0774] Follow the instructions in the application and speak in front of the microphone.

[0775] Step 5:

[0776] The device collects sensor data and emotion data.

[0777] The device collects biometric information such as the user's breathing patterns, voice frequency, and muscle movements in real time.

[0778] The collected data is temporarily stored in memory.

[0779] At the same time, the emotion engine analyzes the user's voice and biometric information to collect emotional data.

[0780] Step 6:

[0781] The terminal transmits the collected data to the server.

[0782] The collected biometric and emotional data is organized and sent to a server via the Internet.

[0783] A notification that data transmission is complete is displayed to the user.

[0784] Step 7:

[0785] The server receives the data and analyzes it using the generating AI.

[0786] The server prepares the received data for analysis.

[0787] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[0788] The emotional data recognized by the emotion engine is also analyzed to personalize the feedback content.

[0789] Step 8:

[0790] The server generates the feedback.

[0791] The server generates specific advice in text format based on the analysis results.

[0792] Generative AI is used to create sample audio of ideal pronunciation.

[0793] The advice content is adjusted according to the emotions recognized by the emotion engine, and feedback is generated that takes into consideration the user's psychological state.

[0794] Step 9:

[0795] The device provides feedback to the user.

[0796] The terminal displays the feedback received from the server to the user.

[0797] The application interface provides users with detailed advice and ideal vocalization samples, and also provides personalized advice based on emotions recognized by the emotion engine.

[0798] The above is a flow of specific processing steps for carrying out the invention based on the claims.

[0799] Example 2

[0800] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0801] Conventional voice training systems provide feedback based solely on the user's vocal data and are unable to provide personalized advice that takes into account the user's emotional state. This limits the effectiveness of training. The present invention aims to enable more personalized training by recognizing not only the user's biometric information but also their emotional state and incorporating this information into the feedback.

[0802] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting biometric information when the user speaks using a sensor; means for recognizing emotional data when the user speaks using the sensor; means for transmitting the collected biometric information and emotional data to the server; means for analyzing the collected biometric information and emotional data using a generative AI model and identifying areas for improvement in the speech; means for generating specific advice and ideal speech samples based on the analysis results; and means for providing the advice and ideal speech samples transmitted from the server to the user on the terminal. This enables personalized training that takes the user's emotional state into consideration.

[0803] ---

[0804] A "sensor" is a device that collects biometric information and emotional data when a user speaks.

[0805] The "server" is an entity that analyzes the collected biometric information and emotional data, generates feedback, and sends it to the terminal.

[0806] A "generative AI model" is an algorithm that analyzes collected data, identifies areas for improvement in vocalization, and generates specific advice and samples of ideal vocalizations.

[0807] "Biometric information" refers to breathing patterns, voice frequencies and muscle movements acquired when the user speaks.

[0808] "Emotion data" is data that indicates the emotional state of the user that can be inferred from the tone of the user's voice and biological information.

[0809] A "terminal" is a device used by a user that receives and displays feedback provided by a server.

[0810] "Advice" refers to specific instructions or suggestions that the generative AI model gives to the user to improve their speech based on the analysis results.

[0811] "Ideal speech samples" refer to the best speech examples created by the generative AI model for users to refer to.

[0812] ---

[0813] This invention relates to a voice training system that utilizes sensors, terminals, a server, a generative AI model, and an emotion engine. The system aims to realize more personalized training by recognizing not only the user's biometric information when speaking but also the user's emotions and providing feedback.

[0814] System Overview

[0815] 1. Launching the application

[0816] A user launches a voice training app on their smartphone or tablet. When the application is launched, the device begins the initialization process for the sensors and emotion engine. The message displayed is "Preparing sensors and emotion engine."

[0817] 2. Sensor data collection

[0818] When a user selects training mode and starts speaking, sensors collect biometric information from the user. For example, a microphone captures the voice, a breathing pattern sensor measures the rhythm and depth of breathing, and an electromyography sensor detects muscle movement. The device integrates this data and stores it in memory in real time.

[0819] 3. Collecting Emotional Data

[0820] The device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state, and the recognized emotional data is also stored on the device in real time.

[0821] 4. Data transmission

[0822] The device transmits the collected biometric and emotional data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[0823] 5. AI-based data analysis

[0824] Based on the data received by the server, a detailed analysis is performed using a generative AI model. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account and adjusts the feedback content. Specifically, the AI ​​analyzes the data and returns the analysis results to the server.

[0825] 6. Generate feedback

[0826] The server generates feedback to provide to the user based on the analysis results. The generative AI model generates sample speech of ideal pronunciation along with specific advice. The content of the advice is also adjusted based on the emotional data recognized by the emotion engine.

[0827] 7. Providing Feedback

[0828] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[0829] The specific hardware, software, and generative AI models used

[0830] Hardware:

[0831] Microphone: Used to capture audio data.

[0832] Breathing pattern sensor: Measures the rhythm and depth of the user's breathing.

[0833] Myoelectric sensor: Detects muscle movement.

[0834] Smartphone or tablet: A device on which the application runs.

[0835] software:

[0836] Voice training application: Interacts with the user.

[0837] Emotion engine: Recognizes emotions by analyzing the user's tone of voice and biometric information.

[0838] Server software: Uses generative AI models to analyze data and generate feedback.

[0839] Examples of concrete examples and prompts

[0840] Specific examples

[0841] The user taps the voice training app on their smartphone's home screen to launch it. The first time the app is launched, pairing with the sensor device is required. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine." When the user selects training mode and begins speaking, the sensor collects breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory. While speaking, the emotion engine analyzes the user's voice and biometric information to recognize their emotions in real time. This data is sent from the device to the server. The server uses a generative AI to analyze the received data, identifying pitch variations, duration fluctuations, breathing irregularities, and other factors to identify areas for improvement in the voice. It also analyzes emotion data and personalizes the feedback. Based on the analysis results, the server generates feedback to provide to the user and creates a sample voice of the ideal voice. The device receives the feedback sent from the server and presents it to the user on the app interface. The user then reviews detailed advice and sample voices of the ideal voice, and receives personalized advice based on the emotion data.

[0842] Prompt Sentence Examples

[0843] "How do I launch the Voice Training app on my smartphone and complete the sensor pairing?"

[0844] "While making the speech, explain how the sensor collects the data."

[0845] "Please explain in detail how the emotion engine recognizes and collects the user's emotions while speaking."

[0846] The above is a description of the mode for carrying out the invention. This allows users to receive scientifically and individually optimized voice training that was not possible with conventional methods. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[0847] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0848] Step 1:

[0849] The user launches the application

[0850] A user launches a voice training app on their smartphone or tablet. When the app launches, the device begins the initialization process for the sensors and emotion engine.

[0851] Input: Tap the app icon

[0852] Output: The sensor and emotion engine initialization is complete and the message "Preparing the sensor and emotion engine" is displayed to the user.

[0853] Step 2:

[0854] Sensor data collection

[0855] When a user selects training mode and starts speaking, sensors collect biometric information from the user's speech, including breathing patterns, voice frequency, and muscle movements. The device integrates this data and stores it in memory in real time.

[0856] Input: User's speech data

[0857] Output: Breathing patterns, voice frequency, and muscle movement data are stored in the device's memory.

[0858] Step 3:

[0859] Collecting Emotional Data

[0860] While speaking, the device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state. The recognized emotional data is also stored in memory in real time.

[0861] Input: User's voice tone, biometric information

[0862] Output: The user's emotion data is stored in the device's memory.

[0863] Step 4:

[0864] Sending data

[0865] The device transmits the collected biometric and emotional data to the server using a secure communication protocol (HTTPS).

[0866] Input: User breathing patterns, voice frequency, muscle movements, emotional data

[0867] Output: Data is sent to the server.

[0868] Step 5:

[0869] AI-powered data analysis

[0870] The server then uses a generative AI model to perform a detailed analysis of the received data. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account to personalize the feedback.

[0871] Input: collected biometric information, emotional data

[0872] Output: Analysis results and feedback

[0873] Step 6:

[0874] Generate feedback

[0875] The server generates feedback to provide to the user based on the analysis results, uses a generative AI model to generate sample speech of ideal utterances, and adjusts the content of advice based on the user's emotions recognized by the emotion engine.

[0876] Input: Analysis results

[0877] Output: Specific advice and sample audio of ideal pronunciation

[0878] Step 7:

[0879] Providing Feedback

[0880] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[0881] Input: Feedback sent by the server

[0882] Output: Display feedback to the user

[0883] The above is the processing flow of the program for this system. By including the input and output at each step and the specific operations, the operation of the entire system becomes clear.

[0884] (Application example 2)

[0885] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0886] Conventional voice training systems are limited in their effectiveness because they rely only on feedback based on the user's biometric information and are unable to consider the user's emotional state. Furthermore, there is a lack of systems that provide real-time feedback on performance in virtual worlds, making it difficult for users to improve immediately.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting collected biometric information and emotional data to the server, means for analyzing the collected biometric information and emotional data using a generation AI and identifying areas for improvement in vocalization, and means for generating specific advice and ideal vocalization samples based on the areas for improvement. This provides personalized feedback that takes the user's emotional state into consideration, enabling effective real-time improvements in performance in the virtual world.

[0888] A "sensor" is a device for collecting biometric information when a user speaks.

[0889] "Biometric information" is data such as a user's breathing patterns, voice frequency, and muscle movements.

[0890] "Emotion data" is data obtained by analyzing the user's emotional state.

[0891] The "server" is a computer system that analyzes the collected biometric and emotional data and generates feedback.

[0892] "Generative AI" is a type of artificial intelligence that uses collected data to generate vocal improvements and ideal vocal samples.

[0893] "Analysis" refers to the process of using collected biometric and emotional data to identify areas for vocal improvement.

[0894] "Advice" refers to specific instructions for improvement provided to the user.

[0895] An "ideal speech sample" is a voice sample of the desired speech that users should aim for, created by generative AI.

[0896] "Terminal" means a device used by a user that receives and displays feedback sent from the server.

[0897] A "virtual world" is an imaginary environment or space generated by a computer system.

[0898] "Real-time feedback" refers to feedback that is provided immediately in response to a user's actions.

[0899] This invention relates to a voice training system that uses sensors, terminals, servers, generative AI, and emotional data. It recognizes the user's biometric information and emotional state when speaking, and provides personalized feedback based on that information, thereby enabling more effective training and real-time feedback in a virtual world.

[0900] System configuration

[0901] The system consists of the following hardware and software:

[0902] Sensor: A device that collects a user's breathing patterns, voice frequencies, and muscle movements

[0903] Device: The device used by the user, such as a smartphone or tablet.

[0904] Server: A computer system that analyzes collected biometric and emotional data and generates feedback.

[0905] Generative AI: Artificial intelligence that generates vocal improvements and ideal vocal samples

[0906] Emotion Engine: A software module that analyzes the user's emotional state

[0907] Implementation details

[0908] 1. User launches application:

[0909] The user launches the voice training app on their device. Pairing with the sensor device is required. When the app is launched for the first time, a message confirming connection to the sensor device is displayed.

[0910] 2. Biometric and emotional data collection:

[0911] Sensors collect the user's breathing patterns, voice frequency, and muscle movements in real time, while an emotion engine analyzes the user's voice and biometric data to recognize the user's emotional state. This data is temporarily stored on the device.

[0912] 3. Data transmission to the server:

[0913] The collected biometric and emotional data is sent from the device to a server, which then prepares the data for analysis.

[0914] 4. Data Analysis:

[0915] The server uses generative AI to analyze biometric and emotional data to identify areas for improvement in the user's vocalizations and adjusts the feedback content to take into account the perceived emotional state.

[0916] 5. Feedback Generation:

[0917] Based on the analysis results, the server generates specific advice and ideal speech samples. The generated feedback is provided in a personalized format, taking into account the user's emotional state.

[0918] 6. Providing Feedback:

[0919] The device receives the feedback sent from the server and displays it to the user, who can then play back and check detailed advice and sample voices of ideal pronunciation. Real-time feedback is also provided during performance in the virtual world.

[0920] Specific examples

[0921] For example, when a singer performs on a virtual stage, sensors capture their voice frequency and breathing patterns, and the emotion engine recognizes the user's level of tension. This data is sent to a server, and the AI ​​generates feedback such as "Your pitch is too high. Relax a bit and stabilize your pitch," and provides this feedback to the user in real time via their device.

[0922] Example of an input prompt for a generative AI model:

[0923] Prompt: Generate specific feedback to provide to the user based on the following biometric and audio data:

[0924] Biometric information: breathing pattern = [0.7], muscle movement = [1.3]

[0925] Audio data: frequency=[250 Hz], volume=[1.0]

[0926] Emotion: [Tension]

[0927] Feedback statement:

[0928] "Your pitch is too high. Relax a bit and stabilize your pitch. Try taking deep breaths and relaxing techniques."

[0929] This allows users to instantly improve their vocal technique and perform better in virtual environments.

[0930] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0931] Step 1:

[0932] The user launches the application. The user launches the voice training app on their device and pairs it with the sensor device. A connection confirmation message is displayed the first time the app is launched. The input data is the user's operation information, and the output data is the connection status with the sensor device.

[0933] Step 2:

[0934] The sensor collects biometric information when the user speaks. The sensor captures the user's breathing pattern, voice frequency, and muscle movement in real time. The collected data is temporarily stored on the device. The input data is the user's biometric information, and the output data is the collected biometric information.

[0935] Step 3:

[0936] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the collected biometric information and voice data to recognize the user's emotional state. The analysis results are saved on the device. The input data is biometric information and voice data, and the output data is emotion data.

[0937] Step 4:

[0938] The device sends the collected biometric information and emotional data to the server. The device sends the temporarily stored data to the server. The server receives these data. The input data is the biometric information and emotional data, and the output data is the data sent to the server.

[0939] Step 5:

[0940] The server analyzes the data using a generation AI. The generation AI analyzes biometric and emotional data to identify areas for improvement in the user's speech. At the same time, it takes the emotional data into account and adjusts the feedback content. The input data are biometric and emotional data, and the output data are areas for improvement and the adjusted feedback content.

[0941] Step 6:

[0942] The server generates specific advice and ideal speech samples. Using a generation AI, it generates specific advice and ideal speech sample audio to provide to the user. The input data are areas for improvement and feedback, and the output data are specific advice and ideal speech samples.

[0943] Step 7:

[0944] The terminal provides the generated feedback to the user. The terminal receives the advice and voice sample sent from the server and displays them to the user. The user can play and check the detailed advice and ideal voice sample voice. The input data is the feedback from the server, and the output data is the feedback display to the user.

[0945] Step 8:

[0946] It provides real-time feedback in the virtual world. Data is collected and analyzed again in real time during performance, and immediate feedback is given. This allows users to immediately identify areas for improvement and improve their performance. The input data is biometric and emotional data during performance, and the output data is real-time feedback.

[0947] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0948] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0949] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0950] [Third embodiment]

[0951] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0952] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0953] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0954] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0955] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0956] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0957] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0958] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0959] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0960] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0961] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0962] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0963] This invention is a system for scientifically and easily conducting voice training, and utilizes sensors, terminals, servers, and generation AI.

[0964] System Overview

[0965] 1. The user launches the application

[0966] The user launches a voice training application on a device such as a smartphone or tablet.

[0967] When the application is launched, the system begins arming the sensors.

[0968] 2. Sensor data collection

[0969] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[0970] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[0971] 3. Data transmission

[0972] The terminal transmits the collected biometric information to the server.

[0973] In this case, the terminal has a means for transmitting data to a server via a network such as the Internet.

[0974] 4. AI-based data analysis

[0975] Based on the data received by the server, the data is analyzed using generative AI.

[0976] The AI ​​identifies vocal problems (for example, inconsistencies in pitch) and areas for improvement (for example, practice to stabilize pitch).

[0977] 5. Generate feedback

[0978] The server generates feedback based on the results of the AI ​​analysis.

[0979] The feedback includes specific advice and examples of ideal utterances, which are created by generative AI.

[0980] 6. Providing Feedback

[0981] The terminal provides the user with the feedback sent from the server.

[0982] Through the application interface, users can view the feedback (advice and samples of ideal pronunciation).

[0983] Specific examples

[0984] 1. Launching the application

[0985] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor."

[0986] 2. Sensor data collection

[0987] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[0988] 3. Data transmission

[0989] The collected sensor data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes detailed information about the user's breathing patterns, voice frequency, and muscle movements.

[0990] 4. AI-based data analysis

[0991] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for vocal improvement. For example, it identifies specific practice methods for stabilizing pitch.

[0992] 5. Generate feedback

[0993] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample speech of ideal pronunciation created by the AI, allowing the user to understand specifically what points need improvement.

[0994] 6. Providing Feedback

[0995] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and check detailed advice and sample voices of ideal pronunciation. The user can then use this information to carry out daily voice training.

[0996] The above is a detailed description of the embodiment of the present invention. This system enables users to perform effective voice training based on scientific data, regardless of time or place.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] A user launches an application on a smartphone or tablet.

[1000] The user taps to open the voice training app on their device.

[1001] When the application is launched, a message will appear indicating that the sensor is ready.

[1002] Step 2:

[1003] The device initializes the sensor.

[1004] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[1005] A device initialization message will appear letting the user know that it is ready.

[1006] Step 3:

[1007] The user selects training mode and begins speaking.

[1008] The user selects "Start Training" from the application menu.

[1009] Follow the instructions in the application and speak in front of the microphone.

[1010] Step 4:

[1011] The device collects sensor data.

[1012] The device collects real-time data such as the user's breathing patterns, voice frequency, and muscle movements.

[1013] The collected data is temporarily stored in memory.

[1014] Step 5:

[1015] The terminal transmits the collected data to the server.

[1016] The collected biometric information is organized and sent to a server via the Internet.

[1017] Display a notification that data transmission is complete.

[1018] Step 6:

[1019] The server receives the data and analyzes it using the generating AI.

[1020] The server receives the transmitted data and prepares it for analysis.

[1021] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[1022] Step 7:

[1023] The server generates the feedback.

[1024] The server generates specific advice in text format based on the analysis results.

[1025] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[1026] Step 8:

[1027] The device provides feedback to the user.

[1028] The terminal displays the feedback received from the server to the user.

[1029] Within the application interface, users can view advice and samples of ideal pronunciation.

[1030] This explains the specific processing flow of the program and the detailed operation at each step.

[1031] Example 1

[1032] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1033] Conventional voice training requires specialized knowledge and equipment, making it difficult for average users to easily practice based on scientific data. It is also difficult to objectively evaluate one's own vocal performance and find effective ways to improve it. To solve this problem, voice training must be something that users can do regardless of time or place, and that training must be based on scientific data.

[1034] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1035] In this invention, the server includes a means for analyzing the received biometric information using a generative AI model and identifying areas for vocal improvement, a means for generating specific advice and an ideal vocal sample based on the areas for improvement, and a means for the generated ideal vocal sample to be a voice sample created by the generative AI model, thereby enabling users to receive accurate and effective vocal training based on scientific data without being bound by time or place.

[1036] A "sensor" is a device for collecting biometric information when a user speaks.

[1037] A "terminal" is a device operated by a user, which temporarily stores collected data and has the function of transmitting the data to a server.

[1038] "Server" means a computer system that receives data transmitted from a terminal via a network and generates analysis and feedback using a generative AI model.

[1039] The "generative AI model" is an artificial intelligence algorithm that analyzes problems and areas for improvement in vocalization based on collected biometric information and generates ideal vocalization samples.

[1040] "Biometric information" refers to data such as the user's breathing pattern, voice frequency, and muscle movements when speaking.

[1041] A "prompt sentence" is an instruction sentence that prompts the user to make a specific utterance, and is provided as a guideline during training.

[1042] "Feedback" is specific advice and ideal vocalization samples generated by the server based on the results of analysis using a generative AI model.

[1043] "Device" is a general term for data collection equipment such as sensors and terminals operated by users.

[1044] "Network" refers to the overall communications infrastructure for sending and receiving data, including the Internet and local area networks.

[1045] "Data integration" is the process of combining multiple biometric data sets collected from sensors into a single data set.

[1046] The "HTTPS protocol" is an encrypted communication protocol for securely sending and receiving data over the Internet.

[1047] The present invention is a system for scientifically and easily conducting voice training, which utilizes sensors, terminals, a server, and a generative AI model.

[1048] The system is configured as follows:

[1049] Sensor: A device that collects biometric information (breathing patterns, voice frequency, muscle movements) when the user speaks.

[1050] Terminal: A device operated by the user, such as a smartphone or tablet, that temporarily stores data from sensors and transmits it to a server as needed.

[1051] Server: A computer system that receives data sent from the device and uses a generative AI model to analyze the data and generate feedback.

[1052] Generative AI model: An artificial intelligence algorithm that analyzes speech problems and areas for improvement based on collected biometric information, and generates ideal speech samples.

[1053] System Overview

[1054] Launching the application

[1055] The user launches the voice training application on a device such as a smartphone or tablet. After launching, the application begins preparing the sensor and instructs the user to perform the pairing process.

[1056] Sensor data collection

[1057] The user selects training mode and begins speaking as instructed by the application. The sensors collect breathing patterns, voice frequencies, and muscle movements in real time and temporarily store them in the device's memory.

[1058] Sending data

[1059] The terminal packages the collected biometric data and sends it to a server over the network using the HTTPS protocol, encrypting the data.

[1060] AI-powered data analysis

[1061] The server inputs the received data into a generative AI model, which analyzes pitch variations and irregular breathing patterns to identify areas for improvement and problems with vocalization. For example, the AI ​​uses machine learning libraries such as TensorFlow.

[1062] Generate feedback

[1063] The server generates feedback based on the analysis results, including specific areas for improvement and sample speech for ideal pronunciation. The generative AI model generates the speech samples.

[1064] Providing Feedback

[1065] The terminal displays the feedback sent from the server to the user, who can then review the feedback through the application interface and use it to improve their training.

[1066] Specific examples

[1067] Prompt Sentence Examples

[1068] "Say the following clearly and loudly: a-e-i-o"

[1069] After this instruction, the user starts recording and the sensors collect data.

[1070] This system allows users to easily perform effective voice training based on scientific data anywhere.

[1071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1072] Step 1:

[1073] Launching the application

[1074] The user launches a voice training application on a device such as a smartphone or tablet.

[1075] The device will launch the application and display the home screen. When launched for the first time, it will display a message indicating pairing with the sensor device.

[1076] Input: User taps to launch the app

[1077] Output: Home screen display, sensor preparation instructions

[1078] Step 2:

[1079] Sensor data collection

[1080] The user selects training mode and begins speaking as instructed by the application, such as prompting them to "Say the following clearly and loudly: a-e-i-o."

[1081] Sensors capture breathing patterns, voice frequencies, and muscle movements in real time to capture this data.

[1082] The terminal integrates the data received from the sensors and temporarily stores it in memory.

[1083] Input: User's speech data

[1084] Output: Sensor data stored on the device

[1085] Step 3:

[1086] Sending data

[1087] The device packages the collected biometric information and sends it over the network to a server, encrypting the data using the HTTPS protocol.

[1088] The server stores the received data in a database and returns a reception confirmation response to the terminal.

[1089] Input: Sensor data stored on the device

[1090] Output: Data sent to the server, acknowledgement response

[1091] Step 4:

[1092] AI-powered data analysis

[1093] The server inputs the received data into a generative AI model.

[1094] Generative AI models analyze pitch variations and breathing irregularities to identify areas for improvement and problems with vocalization. This analysis is performed using machine learning libraries such as TensorFlow.

[1095] The server stores the AI ​​analysis results in a database.

[1096] Input: Sensor data sent to the server

[1097] Output: Analysis results

[1098] Step 5:

[1099] Generate feedback

[1100] The server uses a generative AI model to generate feedback for the user based on the analysis results, including specific areas for improvement and audio samples of ideal pronunciation.

[1101] A generative AI model generates sample audio of ideal utterances.

[1102] The server packages the generated feedback and sample audio and prepares it for transmission to the user's device.

[1103] Input: Analysis results

[1104] Output: Feedback data and sample audio

[1105] Step 6:

[1106] Providing Feedback

[1107] The terminal receives the feedback data sent from the server and displays it to the user.

[1108] The user checks the feedback content (specific advice and sample audio of ideal pronunciation) through the application interface.

[1109] Input: Feedback data sent from the server

[1110] Output: Feedback display to the user

[1111] The above is the specific flow of processing by this system.

[1112] (Application example 1)

[1113] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1114] Conventional autonomous vehicles do not provide accurate and timely driving assistance based on user voice commands, so it is necessary to improve the user experience and the quality of safe driving.In addition, there is a lack of systems that can analyze the user's spoken voice and provide appropriate feedback, so a consistent solution that combines both is required.

[1115] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1116] In this invention, the server includes: means for collecting biometric information from a sensor when the user speaks; means for transmitting the collected biometric information to the server; means for the server to analyze the collected biometric information using a generation AI and identify areas for improvement in the user's speech; means for the server to generate specific advice and ideal speech samples based on the areas for improvement; means for the terminal to provide the user with the advice and ideal speech samples transmitted from the server; means for collecting the user's voice in the vehicle and analyzing driving instructions and speech data; and means for providing optimal voice instructions while driving based on the analyzed data. This enables consistent provision of accurate and timely driving assistance based on the user's voice instructions and feedback on speech.

[1117] A "sensor" is a device for collecting biometric information when a user speaks.

[1118] "Biometric information" is data obtained from the user's body, such as breathing patterns, voice frequencies, and muscle movements.

[1119] A "terminal" is an electronic device such as a smartphone or tablet operated by a user, or an in-vehicle information system.

[1120] The "server" is an information processing device that receives collected biometric information and analyzes the data using the generation AI.

[1121] "Generative AI" is an artificial intelligence technology that analyzes collected biometric information, identifies areas for improvement in the user's vocalization, and generates samples of ideal vocalizations.

[1122] "Advice" is specific instructions or suggestions provided to the user for improvements to the speech identified by the generative AI.

[1123] An "ideal speech sample" is a speech sample created by generative AI that users should emulate.

[1124] "In-vehicle voice collection means" means a means for collecting a user's voice in real time using microphones or other sensors installed in an autonomous vehicle.

[1125] "Driving instructions" are voice guides related to driving provided to the user, such as route guidance to the destination and operation instructions while driving.

[1126] "Voice instruction optimization" means analyzing the user's voice data and providing driving instructions with optimal timing and content based on that information.

[1127] The present invention provides a system for analyzing voice instructions from a user of an autonomous vehicle and providing accurate and timely driving assistance and feedback regarding speech. Specific embodiments for carrying out the present invention are described below.

[1128] System Overview

[1129] 1. Sensor Preparation

[1130] Microphones and other necessary sensors will be placed inside the autonomous vehicle to prepare for collecting biometric information when the user speaks.

[1131] 2. Collection of audio data

[1132] When the user gives a voice command, the microphone and sensors collect the voice in real time.

[1133] The data collected includes biometric information such as breathing patterns, voice frequencies, and muscle movements.

[1134] 3. Data transmission

[1135] The terminal temporarily stores the collected data and transmits it to a server via the Internet.

[1136] 4. Data Analysis

[1137] The server analyzes the received data using a generative AI model (e.g., GPT-4), analyzing pitch fluctuations, duration variations, and breathing irregularities in the speech to identify areas for improvement in the voice.

[1138] 5. Generate feedback

[1139] Based on the analysis results, the server generates feedback to provide to the user, including specific advice and sample audio of ideal pronunciation created by the generation AI.

[1140] 6. Providing Feedback

[1141] The terminal receives the feedback sent from the server and provides it to the user through a display or audio device in the vehicle.

[1142] System configuration and operation

[1143] This system consists of the following hardware and software:

[1144] Hardware

[1145] Microphone: Installed inside the vehicle to collect the user's voice.

[1146] Sensors: Detect breathing patterns, voice frequencies, and muscle movements.

[1147] On-board computer (Edge Computing Device): Temporarily stores collected data and sends it to a server.

[1148] Display and audio devices: Provide feedback to the user.

[1149] software

[1150] Generative AI models (e.g., GPT-4): Analyze voice data and generate feedback.

[1151] Data collection and transmission software framework (e.g., TensorFlow, PyTorch): Responsible for data preprocessing and transmission.

[1152] Databases for real-time data processing (e.g., Firebase, AWS DynamoDB): Store and manage data.

[1153] Program processing and specific examples

[1154] Below is a concrete example of how the system works.

[1155] 1. Collection and Analysis

[1156] When a user gives a voice command such as "Turn left at the next traffic light," microphones and sensors collect voice data and associated biometric information.

[1157] 2. Data transmission and analysis

[1158] The collected data is sent from the onboard computer to a server where it is analyzed by a generative AI model.

[1159] The analysis results in the generation of feedback regarding voice command optimization and pronunciation (e.g., "Your pitch is unstable; please speak more slowly next time").

[1160] 3. Providing Feedback

[1161] The onboard computer receives the analysis results and provides feedback to the user via a display and audio device.

[1162] Prompt Sentence Examples

[1163] User says: Turn left at the next light.

[1164] Task: Analyze the user's pronunciation and speech patterns and suggest improvements to voice guidance, especially optimizing instructions to the next traffic light.

[1165] Example output: "Turn left at the next traffic light. Then go straight for 500 meters."

[1166] This allows users to receive accurate and timely driving assistance while also receiving feedback on areas for improvement in their speech, enabling an overall safer and more comfortable driving experience.

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1:

[1169] The user issues a voice command. The input is the user's voice data, which is collected by microphones and sensors in the car. The collected data includes breathing patterns, voice frequency, and biometric information such as muscle movements.

[1170] Step 2:

[1171] The terminal temporarily stores the collected biometric information and performs data preprocessing. The input is biometric information, which is converted to a format for transmission to the server. The output is formatted biometric information.

[1172] Step 3:

[1173] The terminal transmits the formatted biometric information to the server via the Internet. At this stage, the input is the formatted biometric information, and the output is a transmission success message to the server.

[1174] Step 4:

[1175] The server analyzes the received data using a generative AI model (e.g., GPT-4). The input is the collected biometric information, and data calculations identify areas for optimizing voice instructions and improving speech production. The output is the analysis results.

[1176] Step 5:

[1177] The server generates feedback based on the analysis results. The input is the analysis results, and the generative AI model is used to generate specific advice and sample audio of ideal pronunciation. The output is feedback data.

[1178] Step 6:

[1179] The server sends the generated feedback data to the terminal. The input is the feedback data, and the output is a transmission success message to the terminal.

[1180] Step 7:

[1181] The terminal receives the feedback data sent from the server and provides it to the user through the in-car display or audio device. The input is the feedback data, and the output is specific advice and audio samples that are displayed or played to the user.

[1182] This allows the user to receive accurate and timely driving assistance based on voice instructions, while also receiving feedback on areas for improvement in their speech.

[1183] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1184] The present invention relates to a voice training system that utilizes sensors, terminals, servers, generative AI, and an emotion engine, and realizes more personalized training by recognizing not only the user's biometric information when speaking, but also the user's emotions and providing feedback.

[1185] System Overview

[1186] 1. The user launches the application

[1187] The user launches the voice training app on their smartphone or tablet. When the app launches, a message appears indicating that the sensors and emotion engine are ready.

[1188] 2. Sensor data collection

[1189] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[1190] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[1191] 3. Collecting Emotional Data

[1192] The emotion engine installed in the device recognizes the user's emotions based on their voice and biometric information.

[1193] Recognized emotion data is also stored on the device in real time.

[1194] 4. Data transmission

[1195] The device transmits the collected biometric information and emotion data to the server.

[1196] The transmitted data includes detailed information about the user's breathing patterns, voice frequencies, muscle movements, and perceived emotions.

[1197] 5. AI-based data analysis

[1198] Based on the data received by the server, the data is analyzed using generative AI.

[1199] The AI ​​analyzes pitch fluctuations, vocal duration, and breathing timing to identify areas for vocal improvement, and also takes emotional data into account to tailor feedback.

[1200] 6. Generate feedback

[1201] The server generates specific advice in text format based on the analysis results, and the advice content is adjusted based on the user's emotions as recognized by the emotion engine.

[1202] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[1203] 7. Providing Feedback

[1204] The terminal provides the feedback received from the server to the user.

[1205] Through the application interface, users can view feedback (advice and ideal vocalization samples), and personalized advice is provided based on emotions recognized by the emotion engine.

[1206] Specific examples

[1207] 1. Launching the application

[1208] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine."

[1209] 2. Sensor data collection

[1210] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[1211] 3. Collecting Emotional Data

[1212] While speaking, the emotion engine analyzes the user's voice and biometric information to recognize the user's emotions in real time. Emotional data is also stored on the device and integrated with other biometric information.

[1213] 4. Data transmission

[1214] The collected biometric and emotional data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes details on the user's breathing patterns, voice frequency, muscle movements, and recognized emotions.

[1215] 5. AI-based data analysis

[1216] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for improvement in the voice. At the same time, it also analyzes emotions recognized by the emotion engine to personalize the feedback.

[1217] 6. Generate feedback

[1218] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample audio of ideal speech created by the generation AI. It also includes personalized advice based on the user's emotions recognized by the emotion engine, allowing the user to understand appropriate areas for improvement based on their own emotional state.

[1219] 7. Providing Feedback

[1220] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and review detailed advice and sample audio of ideal speech. Additionally, personalized advice is provided based on the user's emotions as recognized by the emotion engine.

[1221] This invention allows users to receive scientifically and individually optimized voice training that was previously unavailable. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] The user launches an application.

[1225] Users simply tap to launch the voice training app on their smartphone or tablet.

[1226] When the application launches, it displays the message "Preparing sensors and emotion engine."

[1227] Step 2:

[1228] The device initializes the sensor.

[1229] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[1230] A device initialization message will appear letting the user know that it is ready.

[1231] Step 3:

[1232] The device will initialize the emotion engine.

[1233] The emotion engine is activated and ready to analyze the user's voice and biometric information in real time.

[1234] Once initialization is complete, a completion message will be displayed on the terminal.

[1235] Step 4:

[1236] The user selects training mode and begins speaking.

[1237] The user selects "Start Training" from the application menu.

[1238] Follow the instructions in the application and speak in front of the microphone.

[1239] Step 5:

[1240] The device collects sensor data and emotion data.

[1241] The device collects biometric information such as the user's breathing patterns, voice frequency, and muscle movements in real time.

[1242] The collected data is temporarily stored in memory.

[1243] At the same time, the emotion engine analyzes the user's voice and biometric information to collect emotional data.

[1244] Step 6:

[1245] The terminal transmits the collected data to the server.

[1246] The collected biometric and emotional data is organized and sent to a server via the Internet.

[1247] A notification that data transmission is complete is displayed to the user.

[1248] Step 7:

[1249] The server receives the data and analyzes it using the generating AI.

[1250] The server prepares the received data for analysis.

[1251] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[1252] The emotional data recognized by the emotion engine is also analyzed to personalize the feedback content.

[1253] Step 8:

[1254] The server generates the feedback.

[1255] The server generates specific advice in text format based on the analysis results.

[1256] Generative AI is used to create sample audio of ideal pronunciation.

[1257] The advice content is adjusted according to the emotions recognized by the emotion engine, and feedback is generated that takes into consideration the user's psychological state.

[1258] Step 9:

[1259] The device provides feedback to the user.

[1260] The terminal displays the feedback received from the server to the user.

[1261] The application interface provides users with detailed advice and ideal vocalization samples, and also provides personalized advice based on emotions recognized by the emotion engine.

[1262] The above is a flow of specific processing steps for carrying out the invention based on the claims.

[1263] Example 2

[1264] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1265] Conventional voice training systems provide feedback based solely on the user's vocal data and are unable to provide personalized advice that takes into account the user's emotional state. This limits the effectiveness of training. The present invention aims to enable more personalized training by recognizing not only the user's biometric information but also their emotional state and incorporating this information into the feedback.

[1266] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting biometric information when the user speaks using a sensor; means for recognizing emotional data when the user speaks using the sensor; means for transmitting the collected biometric information and emotional data to the server; means for analyzing the collected biometric information and emotional data using a generative AI model and identifying areas for improvement in the speech; means for generating specific advice and ideal speech samples based on the analysis results; and means for providing the advice and ideal speech samples transmitted from the server to the user on the terminal. This enables personalized training that takes the user's emotional state into consideration.

[1267] ---

[1268] A "sensor" is a device that collects biometric information and emotional data when a user speaks.

[1269] The "server" is an entity that analyzes the collected biometric information and emotional data, generates feedback, and sends it to the terminal.

[1270] A "generative AI model" is an algorithm that analyzes collected data, identifies areas for improvement in vocalization, and generates specific advice and samples of ideal vocalizations.

[1271] "Biometric information" refers to breathing patterns, voice frequencies and muscle movements acquired when the user speaks.

[1272] "Emotion data" is data that indicates the emotional state of the user that can be inferred from the tone of the user's voice and biological information.

[1273] A "terminal" is a device used by a user that receives and displays feedback provided by a server.

[1274] "Advice" refers to specific instructions or suggestions that the generative AI model gives to the user to improve their speech based on the analysis results.

[1275] "Ideal speech samples" refer to the best speech examples created by the generative AI model for users to refer to.

[1276] ---

[1277] This invention relates to a voice training system that utilizes sensors, terminals, a server, a generative AI model, and an emotion engine. The system aims to realize more personalized training by recognizing not only the user's biometric information when speaking but also the user's emotions and providing feedback.

[1278] System Overview

[1279] 1. Launching the application

[1280] A user launches a voice training app on their smartphone or tablet. When the application is launched, the device begins the initialization process for the sensors and emotion engine. The message displayed is "Preparing sensors and emotion engine."

[1281] 2. Sensor data collection

[1282] When a user selects training mode and starts speaking, sensors collect biometric information from the user. For example, a microphone captures the voice, a breathing pattern sensor measures the rhythm and depth of breathing, and an electromyography sensor detects muscle movement. The device integrates this data and stores it in memory in real time.

[1283] 3. Collecting Emotional Data

[1284] The device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state, and the recognized emotional data is also stored on the device in real time.

[1285] 4. Data transmission

[1286] The device transmits the collected biometric and emotional data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[1287] 5. AI-based data analysis

[1288] Based on the data received by the server, a detailed analysis is performed using a generative AI model. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account and adjusts the feedback content. Specifically, the AI ​​analyzes the data and returns the analysis results to the server.

[1289] 6. Generate feedback

[1290] The server generates feedback to provide to the user based on the analysis results. The generative AI model generates sample speech of ideal pronunciation along with specific advice. The content of the advice is also adjusted based on the emotional data recognized by the emotion engine.

[1291] 7. Providing Feedback

[1292] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[1293] The specific hardware, software, and generative AI models used

[1294] Hardware:

[1295] Microphone: Used to capture audio data.

[1296] Breathing pattern sensor: Measures the rhythm and depth of the user's breathing.

[1297] Myoelectric sensor: Detects muscle movement.

[1298] Smartphone or tablet: A device on which the application runs.

[1299] software:

[1300] Voice training application: Interacts with the user.

[1301] Emotion engine: Recognizes emotions by analyzing the user's tone of voice and biometric information.

[1302] Server software: Uses generative AI models to analyze data and generate feedback.

[1303] Examples of concrete examples and prompts

[1304] Specific examples

[1305] The user taps the voice training app on their smartphone's home screen to launch it. The first time the app is launched, pairing with the sensor device is required. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine." When the user selects training mode and begins speaking, the sensor collects breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory. While speaking, the emotion engine analyzes the user's voice and biometric information to recognize their emotions in real time. This data is sent from the device to the server. The server uses a generative AI to analyze the received data, identifying pitch variations, duration fluctuations, breathing irregularities, and other factors to identify areas for improvement in the voice. It also analyzes emotion data and personalizes the feedback. Based on the analysis results, the server generates feedback to provide to the user and creates a sample voice of the ideal voice. The device receives the feedback sent from the server and presents it to the user on the app interface. The user then reviews detailed advice and sample voices of the ideal voice, and receives personalized advice based on the emotion data.

[1306] Prompt Sentence Examples

[1307] "How do I launch the Voice Training app on my smartphone and complete the sensor pairing?"

[1308] "While making the speech, explain how the sensor collects the data."

[1309] "Please explain in detail how the emotion engine recognizes and collects the user's emotions while speaking."

[1310] The above is a description of the mode for carrying out the invention. This allows users to receive scientifically and individually optimized voice training that was not possible with conventional methods. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[1311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1312] Step 1:

[1313] The user launches the application

[1314] A user launches a voice training app on their smartphone or tablet. When the app launches, the device begins the initialization process for the sensors and emotion engine.

[1315] Input: Tap the app icon

[1316] Output: The sensor and emotion engine initialization is complete and the message "Preparing the sensor and emotion engine" is displayed to the user.

[1317] Step 2:

[1318] Sensor data collection

[1319] When a user selects training mode and starts speaking, sensors collect biometric information from the user's speech, including breathing patterns, voice frequency, and muscle movements. The device integrates this data and stores it in memory in real time.

[1320] Input: User's speech data

[1321] Output: Breathing patterns, voice frequency, and muscle movement data are stored in the device's memory.

[1322] Step 3:

[1323] Collecting Emotional Data

[1324] While speaking, the device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state. The recognized emotional data is also stored in memory in real time.

[1325] Input: User's voice tone, biometric information

[1326] Output: The user's emotion data is stored in the device's memory.

[1327] Step 4:

[1328] Sending data

[1329] The device transmits the collected biometric and emotional data to the server using a secure communication protocol (HTTPS).

[1330] Input: User breathing patterns, voice frequency, muscle movements, emotional data

[1331] Output: Data is sent to the server.

[1332] Step 5:

[1333] AI-powered data analysis

[1334] The server then uses a generative AI model to perform a detailed analysis of the received data. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account to personalize the feedback.

[1335] Input: collected biometric information, emotional data

[1336] Output: Analysis results and feedback

[1337] Step 6:

[1338] Generate feedback

[1339] The server generates feedback to provide to the user based on the analysis results, uses a generative AI model to generate sample speech of ideal utterances, and adjusts the content of advice based on the user's emotions recognized by the emotion engine.

[1340] Input: Analysis results

[1341] Output: Specific advice and sample audio of ideal pronunciation

[1342] Step 7:

[1343] Providing Feedback

[1344] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[1345] Input: Feedback sent by the server

[1346] Output: Display feedback to the user

[1347] The above is the processing flow of the program for this system. By including the input and output at each step and the specific operations, the operation of the entire system becomes clear.

[1348] (Application example 2)

[1349] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1350] Conventional voice training systems are limited in their effectiveness because they rely only on feedback based on the user's biometric information and are unable to consider the user's emotional state. Furthermore, there is a lack of systems that provide real-time feedback on performance in virtual worlds, making it difficult for users to improve immediately.

[1351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting collected biometric information and emotional data to the server, means for analyzing the collected biometric information and emotional data using a generation AI and identifying areas for improvement in vocalization, and means for generating specific advice and ideal vocalization samples based on the areas for improvement. This provides personalized feedback that takes the user's emotional state into consideration, enabling effective real-time improvements in performance in the virtual world.

[1352] A "sensor" is a device for collecting biometric information when a user speaks.

[1353] "Biometric information" is data such as a user's breathing patterns, voice frequency, and muscle movements.

[1354] "Emotion data" is data obtained by analyzing the user's emotional state.

[1355] The "server" is a computer system that analyzes the collected biometric and emotional data and generates feedback.

[1356] "Generative AI" is a type of artificial intelligence that uses collected data to generate vocal improvements and ideal vocal samples.

[1357] "Analysis" refers to the process of using collected biometric and emotional data to identify areas for vocal improvement.

[1358] "Advice" refers to specific instructions for improvement provided to the user.

[1359] An "ideal speech sample" is a voice sample of the desired speech that users should aim for, created by generative AI.

[1360] "Terminal" means a device used by a user that receives and displays feedback sent from the server.

[1361] A "virtual world" is an imaginary environment or space generated by a computer system.

[1362] "Real-time feedback" refers to feedback that is provided immediately in response to a user's actions.

[1363] This invention relates to a voice training system that uses sensors, terminals, servers, generative AI, and emotional data. It recognizes the user's biometric information and emotional state when speaking, and provides personalized feedback based on that information, thereby enabling more effective training and real-time feedback in a virtual world.

[1364] System configuration

[1365] The system consists of the following hardware and software:

[1366] Sensor: A device that collects a user's breathing patterns, voice frequencies, and muscle movements

[1367] Device: The device used by the user, such as a smartphone or tablet.

[1368] Server: A computer system that analyzes collected biometric and emotional data and generates feedback.

[1369] Generative AI: Artificial intelligence that generates vocal improvements and ideal vocal samples

[1370] Emotion Engine: A software module that analyzes the user's emotional state

[1371] Implementation details

[1372] 1. User launches application:

[1373] The user launches the voice training app on their device. Pairing with the sensor device is required. When the app is launched for the first time, a message confirming connection to the sensor device is displayed.

[1374] 2. Biometric and emotional data collection:

[1375] Sensors collect the user's breathing patterns, voice frequency, and muscle movements in real time, while an emotion engine analyzes the user's voice and biometric data to recognize the user's emotional state. This data is temporarily stored on the device.

[1376] 3. Data transmission to the server:

[1377] The collected biometric and emotional data is sent from the device to a server, which then prepares the data for analysis.

[1378] 4. Data Analysis:

[1379] The server uses generative AI to analyze biometric and emotional data to identify areas for improvement in the user's vocalizations and adjusts the feedback content to take into account the perceived emotional state.

[1380] 5. Feedback Generation:

[1381] Based on the analysis results, the server generates specific advice and ideal speech samples. The generated feedback is provided in a personalized format, taking into account the user's emotional state.

[1382] 6. Providing Feedback:

[1383] The device receives the feedback sent from the server and displays it to the user, who can then play back and check detailed advice and sample voices of ideal pronunciation. Real-time feedback is also provided during performance in the virtual world.

[1384] Specific examples

[1385] For example, when a singer performs on a virtual stage, sensors capture their voice frequency and breathing patterns, and the emotion engine recognizes the user's level of tension. This data is sent to a server, and the AI ​​generates feedback such as "Your pitch is too high. Relax a bit and stabilize your pitch," and provides this feedback to the user in real time via their device.

[1386] Example of an input prompt for a generative AI model:

[1387] Prompt: Generate specific feedback to provide to the user based on the following biometric and audio data:

[1388] Biometric information: breathing pattern = [0.7], muscle movement = [1.3]

[1389] Audio data: frequency=[250 Hz], volume=[1.0]

[1390] Emotion: [Tension]

[1391] Feedback statement:

[1392] "Your pitch is too high. Relax a bit and stabilize your pitch. Try taking deep breaths and relaxing techniques."

[1393] This allows users to instantly improve their vocal technique and perform better in virtual environments.

[1394] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1395] Step 1:

[1396] The user launches the application. The user launches the voice training app on their device and pairs it with the sensor device. A connection confirmation message is displayed the first time the app is launched. The input data is the user's operation information, and the output data is the connection status with the sensor device.

[1397] Step 2:

[1398] The sensor collects biometric information when the user speaks. The sensor captures the user's breathing pattern, voice frequency, and muscle movement in real time. The collected data is temporarily stored on the device. The input data is the user's biometric information, and the output data is the collected biometric information.

[1399] Step 3:

[1400] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the collected biometric information and voice data to recognize the user's emotional state. The analysis results are saved on the device. The input data is biometric information and voice data, and the output data is emotion data.

[1401] Step 4:

[1402] The device sends the collected biometric information and emotional data to the server. The device sends the temporarily stored data to the server. The server receives these data. The input data is the biometric information and emotional data, and the output data is the data sent to the server.

[1403] Step 5:

[1404] The server analyzes the data using a generation AI. The generation AI analyzes biometric and emotional data to identify areas for improvement in the user's speech. At the same time, it takes the emotional data into account and adjusts the feedback content. The input data are biometric and emotional data, and the output data are areas for improvement and the adjusted feedback content.

[1405] Step 6:

[1406] The server generates specific advice and ideal speech samples. Using a generation AI, it generates specific advice and ideal speech sample audio to provide to the user. The input data are areas for improvement and feedback, and the output data are specific advice and ideal speech samples.

[1407] Step 7:

[1408] The terminal provides the generated feedback to the user. The terminal receives the advice and voice sample sent from the server and displays them to the user. The user can play and check the detailed advice and ideal voice sample voice. The input data is the feedback from the server, and the output data is the feedback display to the user.

[1409] Step 8:

[1410] It provides real-time feedback in the virtual world. Data is collected and analyzed again in real time during performance, and immediate feedback is given. This allows users to immediately identify areas for improvement and improve their performance. The input data is biometric and emotional data during performance, and the output data is real-time feedback.

[1411] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1412] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1413] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1414] [Fourth embodiment]

[1415] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1416] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1417] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1418] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1419] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1420] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1421] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1422] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1423] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1424] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1425] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1426] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1427] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1428] This invention is a system for scientifically and easily conducting voice training, and utilizes sensors, terminals, servers, and generation AI.

[1429] System Overview

[1430] 1. The user launches the application

[1431] The user launches a voice training application on a device such as a smartphone or tablet.

[1432] When the application is launched, the system begins arming the sensors.

[1433] 2. Sensor data collection

[1434] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[1435] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[1436] 3. Data transmission

[1437] The terminal transmits the collected biometric information to the server.

[1438] In this case, the terminal has a means for transmitting data to a server via a network such as the Internet.

[1439] 4. AI-based data analysis

[1440] Based on the data received by the server, the data is analyzed using generative AI.

[1441] The AI ​​identifies vocal problems (for example, inconsistencies in pitch) and areas for improvement (for example, practice to stabilize pitch).

[1442] 5. Generate feedback

[1443] The server generates feedback based on the results of the AI ​​analysis.

[1444] The feedback includes specific advice and examples of ideal utterances, which are created by generative AI.

[1445] 6. Providing Feedback

[1446] The terminal provides the user with the feedback sent from the server.

[1447] Through the application interface, users can view the feedback (advice and samples of ideal pronunciation).

[1448] Specific examples

[1449] 1. Launching the application

[1450] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor."

[1451] 2. Sensor data collection

[1452] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[1453] 3. Data transmission

[1454] The collected sensor data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes detailed information about the user's breathing patterns, voice frequency, and muscle movements.

[1455] 4. AI-based data analysis

[1456] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for vocal improvement. For example, it identifies specific practice methods for stabilizing pitch.

[1457] 5. Generate feedback

[1458] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample speech of ideal pronunciation created by the AI, allowing the user to understand specifically what points need improvement.

[1459] 6. Providing Feedback

[1460] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and check detailed advice and sample voices of ideal pronunciation. The user can then use this information to carry out daily voice training.

[1461] The above is a detailed description of the embodiment of the present invention. This system enables users to perform effective voice training based on scientific data, regardless of time or place.

[1462] The processing flow will be explained below.

[1463] Step 1:

[1464] A user launches an application on a smartphone or tablet.

[1465] The user taps to open the voice training app on their device.

[1466] When the application is launched, a message will appear indicating that the sensor is ready.

[1467] Step 2:

[1468] The device initializes the sensor.

[1469] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[1470] A device initialization message will appear letting the user know that it is ready.

[1471] Step 3:

[1472] The user selects training mode and begins speaking.

[1473] The user selects "Start Training" from the application menu.

[1474] Follow the instructions in the application and speak in front of the microphone.

[1475] Step 4:

[1476] The device collects sensor data.

[1477] The device collects real-time data such as the user's breathing patterns, voice frequency, and muscle movements.

[1478] The collected data is temporarily stored in memory.

[1479] Step 5:

[1480] The terminal transmits the collected data to the server.

[1481] The collected biometric information is organized and sent to a server via the Internet.

[1482] Display a notification that data transmission is complete.

[1483] Step 6:

[1484] The server receives the data and analyzes it using the generating AI.

[1485] The server receives the transmitted data and prepares it for analysis.

[1486] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[1487] Step 7:

[1488] The server generates the feedback.

[1489] The server generates specific advice in text format based on the analysis results.

[1490] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[1491] Step 8:

[1492] The device provides feedback to the user.

[1493] The terminal displays the feedback received from the server to the user.

[1494] Within the application interface, users can view advice and samples of ideal pronunciation.

[1495] This explains the specific processing flow of the program and the detailed operation at each step.

[1496] Example 1

[1497] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1498] Conventional voice training requires specialized knowledge and equipment, making it difficult for average users to easily practice based on scientific data. It is also difficult to objectively evaluate one's own vocal performance and find effective ways to improve it. To solve this problem, voice training must be something that users can do regardless of time or place, and that training must be based on scientific data.

[1499] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1500] In this invention, the server includes a means for analyzing the received biometric information using a generative AI model and identifying areas for vocal improvement, a means for generating specific advice and an ideal vocal sample based on the areas for improvement, and a means for the generated ideal vocal sample to be a voice sample created by the generative AI model, thereby enabling users to receive accurate and effective vocal training based on scientific data without being bound by time or place.

[1501] A "sensor" is a device for collecting biometric information when a user speaks.

[1502] A "terminal" is a device operated by a user, which temporarily stores collected data and has the function of transmitting the data to a server.

[1503] "Server" means a computer system that receives data transmitted from a terminal via a network and generates analysis and feedback using a generative AI model.

[1504] The "generative AI model" is an artificial intelligence algorithm that analyzes problems and areas for improvement in vocalization based on collected biometric information and generates ideal vocalization samples.

[1505] "Biometric information" refers to data such as the user's breathing pattern, voice frequency, and muscle movements when speaking.

[1506] A "prompt sentence" is an instruction sentence that prompts the user to make a specific utterance, and is provided as a guideline during training.

[1507] "Feedback" is specific advice and ideal vocalization samples generated by the server based on the results of analysis using a generative AI model.

[1508] "Device" is a general term for data collection equipment such as sensors and terminals operated by users.

[1509] "Network" refers to the overall communications infrastructure for sending and receiving data, including the Internet and local area networks.

[1510] "Data integration" is the process of combining multiple biometric data sets collected from sensors into a single data set.

[1511] The "HTTPS protocol" is an encrypted communication protocol for securely sending and receiving data over the Internet.

[1512] The present invention is a system for scientifically and easily conducting voice training, which utilizes sensors, terminals, a server, and a generative AI model.

[1513] The system is configured as follows:

[1514] Sensor: A device that collects biometric information (breathing patterns, voice frequency, muscle movements) when the user speaks.

[1515] Terminal: A device operated by the user, such as a smartphone or tablet, that temporarily stores data from sensors and transmits it to a server as needed.

[1516] Server: A computer system that receives data sent from the device and uses a generative AI model to analyze the data and generate feedback.

[1517] Generative AI model: An artificial intelligence algorithm that analyzes speech problems and areas for improvement based on collected biometric information, and generates ideal speech samples.

[1518] System Overview

[1519] Launching the application

[1520] The user launches the voice training application on a device such as a smartphone or tablet. After launching, the application begins preparing the sensor and instructs the user to perform the pairing process.

[1521] Sensor data collection

[1522] The user selects training mode and begins speaking as instructed by the application. The sensors collect breathing patterns, voice frequencies, and muscle movements in real time and temporarily store them in the device's memory.

[1523] Sending data

[1524] The terminal packages the collected biometric data and sends it to a server over the network using the HTTPS protocol, encrypting the data.

[1525] AI-powered data analysis

[1526] The server inputs the received data into a generative AI model, which analyzes pitch variations and irregular breathing patterns to identify areas for improvement and problems with vocalization. For example, the AI ​​uses machine learning libraries such as TensorFlow.

[1527] Generate feedback

[1528] The server generates feedback based on the analysis results, including specific areas for improvement and sample speech for ideal pronunciation. The generative AI model generates the speech samples.

[1529] Providing Feedback

[1530] The terminal displays the feedback sent from the server to the user, who can then review the feedback through the application interface and use it to improve their training.

[1531] Specific examples

[1532] Prompt Sentence Examples

[1533] "Say the following clearly and loudly: a-e-i-o"

[1534] After this instruction, the user starts recording and the sensors collect data.

[1535] This system allows users to easily perform effective voice training based on scientific data anywhere.

[1536] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1537] Step 1:

[1538] Launching the application

[1539] The user launches a voice training application on a device such as a smartphone or tablet.

[1540] The device will launch the application and display the home screen. When launched for the first time, it will display a message indicating pairing with the sensor device.

[1541] Input: User taps to launch the app

[1542] Output: Home screen display, sensor preparation instructions

[1543] Step 2:

[1544] Sensor data collection

[1545] The user selects training mode and begins speaking as instructed by the application, such as prompting them to "Say the following clearly and loudly: a-e-i-o."

[1546] Sensors capture breathing patterns, voice frequencies, and muscle movements in real time to capture this data.

[1547] The terminal integrates the data received from the sensors and temporarily stores it in memory.

[1548] Input: User's speech data

[1549] Output: Sensor data stored on the device

[1550] Step 3:

[1551] Sending data

[1552] The device packages the collected biometric information and sends it over the network to a server, encrypting the data using the HTTPS protocol.

[1553] The server stores the received data in a database and returns a reception confirmation response to the terminal.

[1554] Input: Sensor data stored on the device

[1555] Output: Data sent to the server, acknowledgement response

[1556] Step 4:

[1557] AI-powered data analysis

[1558] The server inputs the received data into a generative AI model.

[1559] Generative AI models analyze pitch variations and breathing irregularities to identify areas for improvement and problems with vocalization. This analysis is performed using machine learning libraries such as TensorFlow.

[1560] The server stores the AI ​​analysis results in a database.

[1561] Input: Sensor data sent to the server

[1562] Output: Analysis results

[1563] Step 5:

[1564] Generate feedback

[1565] The server uses a generative AI model to generate feedback for the user based on the analysis results, including specific areas for improvement and audio samples of ideal pronunciation.

[1566] A generative AI model generates sample audio of ideal utterances.

[1567] The server packages the generated feedback and sample audio and prepares it for transmission to the user's device.

[1568] Input: Analysis results

[1569] Output: Feedback data and sample audio

[1570] Step 6:

[1571] Providing Feedback

[1572] The terminal receives the feedback data sent from the server and displays it to the user.

[1573] The user checks the feedback content (specific advice and sample audio of ideal pronunciation) through the application interface.

[1574] Input: Feedback data sent from the server

[1575] Output: Feedback display to the user

[1576] The above is the specific flow of processing by this system.

[1577] (Application example 1)

[1578] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1579] Conventional autonomous vehicles do not provide accurate and timely driving assistance based on user voice commands, so it is necessary to improve the user experience and the quality of safe driving.In addition, there is a lack of systems that can analyze the user's spoken voice and provide appropriate feedback, so a consistent solution that combines both is required.

[1580] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1581] In this invention, the server includes: means for collecting biometric information from a sensor when the user speaks; means for transmitting the collected biometric information to the server; means for the server to analyze the collected biometric information using a generation AI and identify areas for improvement in the user's speech; means for the server to generate specific advice and ideal speech samples based on the areas for improvement; means for the terminal to provide the user with the advice and ideal speech samples transmitted from the server; means for collecting the user's voice in the vehicle and analyzing driving instructions and speech data; and means for providing optimal voice instructions while driving based on the analyzed data. This enables consistent provision of accurate and timely driving assistance based on the user's voice instructions and feedback on speech.

[1582] A "sensor" is a device for collecting biometric information when a user speaks.

[1583] "Biometric information" is data obtained from the user's body, such as breathing patterns, voice frequencies, and muscle movements.

[1584] A "terminal" is an electronic device such as a smartphone or tablet operated by a user, or an in-vehicle information system.

[1585] The "server" is an information processing device that receives collected biometric information and analyzes the data using the generation AI.

[1586] "Generative AI" is an artificial intelligence technology that analyzes collected biometric information, identifies areas for improvement in the user's vocalization, and generates samples of ideal vocalizations.

[1587] "Advice" is specific instructions or suggestions provided to the user for improvements to the speech identified by the generative AI.

[1588] An "ideal speech sample" is a speech sample created by generative AI that users should emulate.

[1589] "In-vehicle voice collection means" means a means for collecting a user's voice in real time using microphones or other sensors installed in an autonomous vehicle.

[1590] "Driving instructions" are voice guides related to driving provided to the user, such as route guidance to the destination and operation instructions while driving.

[1591] "Voice instruction optimization" means analyzing the user's voice data and providing driving instructions with optimal timing and content based on that information.

[1592] The present invention provides a system for analyzing voice instructions from a user of an autonomous vehicle and providing accurate and timely driving assistance and feedback regarding speech. Specific embodiments for carrying out the present invention are described below.

[1593] System Overview

[1594] 1. Sensor Preparation

[1595] Microphones and other necessary sensors will be placed inside the autonomous vehicle to prepare for collecting biometric information when the user speaks.

[1596] 2. Collection of audio data

[1597] When the user gives a voice command, the microphone and sensors collect the voice in real time.

[1598] The data collected includes biometric information such as breathing patterns, voice frequencies, and muscle movements.

[1599] 3. Data transmission

[1600] The terminal temporarily stores the collected data and transmits it to a server via the Internet.

[1601] 4. Data Analysis

[1602] The server analyzes the received data using a generative AI model (e.g., GPT-4), analyzing pitch fluctuations, duration variations, and breathing irregularities in the speech to identify areas for improvement in the voice.

[1603] 5. Generate feedback

[1604] Based on the analysis results, the server generates feedback to provide to the user, including specific advice and sample audio of ideal pronunciation created by the generation AI.

[1605] 6. Providing Feedback

[1606] The terminal receives the feedback sent from the server and provides it to the user through a display or audio device in the vehicle.

[1607] System configuration and operation

[1608] This system consists of the following hardware and software:

[1609] Hardware

[1610] Microphone: Installed inside the vehicle to collect the user's voice.

[1611] Sensors: Detect breathing patterns, voice frequencies, and muscle movements.

[1612] On-board computer (Edge Computing Device): Temporarily stores collected data and sends it to a server.

[1613] Display and audio devices: Provide feedback to the user.

[1614] software

[1615] Generative AI models (e.g., GPT-4): Analyze voice data and generate feedback.

[1616] Data collection and transmission software framework (e.g., TensorFlow, PyTorch): Responsible for data preprocessing and transmission.

[1617] Databases for real-time data processing (e.g., Firebase, AWS DynamoDB): Store and manage data.

[1618] Program processing and specific examples

[1619] Below is a concrete example of how the system works.

[1620] 1. Collection and Analysis

[1621] When a user gives a voice command such as "Turn left at the next traffic light," microphones and sensors collect voice data and associated biometric information.

[1622] 2. Data transmission and analysis

[1623] The collected data is sent from the onboard computer to a server where it is analyzed by a generative AI model.

[1624] The analysis results in the generation of feedback regarding voice command optimization and pronunciation (e.g., "Your pitch is unstable; please speak more slowly next time").

[1625] 3. Providing Feedback

[1626] The onboard computer receives the analysis results and provides feedback to the user via a display and audio device.

[1627] Prompt Sentence Examples

[1628] User says: Turn left at the next light.

[1629] Task: Analyze the user's pronunciation and speech patterns and suggest improvements to voice guidance, especially optimizing instructions to the next traffic light.

[1630] Example output: "Turn left at the next traffic light. Then go straight for 500 meters."

[1631] This allows users to receive accurate and timely driving assistance while also receiving feedback on areas for improvement in their speech, enabling an overall safer and more comfortable driving experience.

[1632] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1633] Step 1:

[1634] The user issues a voice command. The input is the user's voice data, which is collected by microphones and sensors in the car. The collected data includes breathing patterns, voice frequency, and biometric information such as muscle movements.

[1635] Step 2:

[1636] The terminal temporarily stores the collected biometric information and performs data preprocessing. The input is biometric information, which is converted to a format for transmission to the server. The output is formatted biometric information.

[1637] Step 3:

[1638] The terminal transmits the formatted biometric information to the server via the Internet. At this stage, the input is the formatted biometric information, and the output is a transmission success message to the server.

[1639] Step 4:

[1640] The server analyzes the received data using a generative AI model (e.g., GPT-4). The input is the collected biometric information, and data calculations identify areas for optimizing voice instructions and improving speech production. The output is the analysis results.

[1641] Step 5:

[1642] The server generates feedback based on the analysis results. The input is the analysis results, and the generative AI model is used to generate specific advice and sample audio of ideal pronunciation. The output is feedback data.

[1643] Step 6:

[1644] The server sends the generated feedback data to the terminal. The input is the feedback data, and the output is a transmission success message to the terminal.

[1645] Step 7:

[1646] The terminal receives the feedback data sent from the server and provides it to the user through the in-car display or audio device. The input is the feedback data, and the output is specific advice and audio samples that are displayed or played to the user.

[1647] This allows the user to receive accurate and timely driving assistance based on voice instructions, while also receiving feedback on areas for improvement in their speech.

[1648] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1649] The present invention relates to a voice training system that utilizes sensors, terminals, servers, generative AI, and an emotion engine, and realizes more personalized training by recognizing not only the user's biometric information when speaking, but also the user's emotions and providing feedback.

[1650] System Overview

[1651] 1. The user launches the application

[1652] The user launches the voice training app on their smartphone or tablet. When the app launches, a message appears indicating that the sensors and emotion engine are ready.

[1653] 2. Sensor data collection

[1654] Sensors collect biometric information as the user speaks, specifically breathing patterns, voice frequency, and muscle movements.

[1655] The device aggregates data from relevant sensors and temporarily stores the data in real time.

[1656] 3. Collecting Emotional Data

[1657] The emotion engine installed in the device recognizes the user's emotions based on their voice and biometric information.

[1658] Recognized emotion data is also stored on the device in real time.

[1659] 4. Data transmission

[1660] The device transmits the collected biometric information and emotion data to the server.

[1661] The transmitted data includes detailed information about the user's breathing patterns, voice frequencies, muscle movements, and perceived emotions.

[1662] 5. AI-based data analysis

[1663] Based on the data received by the server, the data is analyzed using generative AI.

[1664] The AI ​​analyzes pitch fluctuations, vocal duration, and breathing timing to identify areas for vocal improvement, and also takes emotional data into account to tailor feedback.

[1665] 6. Generate feedback

[1666] The server generates specific advice in text format based on the analysis results, and the advice content is adjusted based on the user's emotions as recognized by the emotion engine.

[1667] Furthermore, generative AI is used to create sample audio of ideal pronunciation.

[1668] 7. Providing Feedback

[1669] The terminal provides the feedback received from the server to the user.

[1670] Through the application interface, users can view feedback (advice and ideal vocalization samples), and personalized advice is provided based on emotions recognized by the emotion engine.

[1671] Specific examples

[1672] 1. Launching the application

[1673] The user taps the voice training app on the smartphone's home screen to launch it. When launched for the first time, the app prompts for pairing with the sensor device. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine."

[1674] 2. Sensor data collection

[1675] The user selects training mode and begins speaking as instructed by the app. The sensors collect breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory.

[1676] 3. Collecting Emotional Data

[1677] While speaking, the emotion engine analyzes the user's voice and biometric information to recognize the user's emotions in real time. Emotional data is also stored on the device and integrated with other biometric information.

[1678] 4. Data transmission

[1679] The collected biometric and emotional data is sent from the device to a server, which receives the data and prepares it for AI analysis. This data includes details on the user's breathing patterns, voice frequency, muscle movements, and recognized emotions.

[1680] 5. AI-based data analysis

[1681] The server analyzes the received data using the generated AI. The AI ​​analyzes pitch fluctuations, duration fluctuations, irregular breathing, and other aspects of the voice to identify areas for improvement in the voice. At the same time, it also analyzes emotions recognized by the emotion engine to personalize the feedback.

[1682] 6. Generate feedback

[1683] Based on the analysis results, the server generates feedback to provide to the user. The feedback includes specific advice and sample audio of ideal speech created by the generation AI. It also includes personalized advice based on the user's emotions recognized by the emotion engine, allowing the user to understand appropriate areas for improvement based on their own emotional state.

[1684] 7. Providing Feedback

[1685] The device receives the feedback sent from the server and displays it to the user. The application interface allows the user to play and review detailed advice and sample audio of ideal speech. Additionally, personalized advice is provided based on the user's emotions as recognized by the emotion engine.

[1686] This invention allows users to receive scientifically and individually optimized voice training that was previously unavailable. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[1687] The processing flow will be explained below.

[1688] Step 1:

[1689] The user launches an application.

[1690] Users simply tap to launch the voice training app on their smartphone or tablet.

[1691] When the application launches, it displays the message "Preparing sensors and emotion engine."

[1692] Step 2:

[1693] The device initializes the sensor.

[1694] The device will activate devices such as the breathing tracker and vocal cord electromyography sensor and check that they are working properly.

[1695] A device initialization message will appear letting the user know that it is ready.

[1696] Step 3:

[1697] The device will initialize the emotion engine.

[1698] The emotion engine is activated and ready to analyze the user's voice and biometric information in real time.

[1699] Once initialization is complete, a completion message will be displayed on the terminal.

[1700] Step 4:

[1701] The user selects training mode and begins speaking.

[1702] The user selects "Start Training" from the application menu.

[1703] Follow the instructions in the application and speak in front of the microphone.

[1704] Step 5:

[1705] The device collects sensor data and emotion data.

[1706] The device collects biometric information such as the user's breathing patterns, voice frequency, and muscle movements in real time.

[1707] The collected data is temporarily stored in memory.

[1708] At the same time, the emotion engine analyzes the user's voice and biometric information to collect emotional data.

[1709] Step 6:

[1710] The terminal transmits the collected data to the server.

[1711] The collected biometric and emotional data is organized and sent to a server via the Internet.

[1712] A notification that data transmission is complete is displayed to the user.

[1713] Step 7:

[1714] The server receives the data and analyzes it using the generating AI.

[1715] The server prepares the received data for analysis.

[1716] The generative AI analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement in vocal production.

[1717] The emotional data recognized by the emotion engine is also analyzed to personalize the feedback content.

[1718] Step 8:

[1719] The server generates the feedback.

[1720] The server generates specific advice in text format based on the analysis results.

[1721] Generative AI is used to create sample audio of ideal pronunciation.

[1722] The advice content is adjusted according to the emotions recognized by the emotion engine, and feedback is generated that takes into consideration the user's psychological state.

[1723] Step 9:

[1724] The device provides feedback to the user.

[1725] The terminal displays the feedback received from the server to the user.

[1726] The application interface provides users with detailed advice and ideal vocalization samples, and also provides personalized advice based on emotions recognized by the emotion engine.

[1727] The above is a flow of specific processing steps for carrying out the invention based on the claims.

[1728] Example 2

[1729] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1730] Conventional voice training systems provide feedback based solely on the user's vocal data and are unable to provide personalized advice that takes into account the user's emotional state. This limits the effectiveness of training. The present invention aims to enable more personalized training by recognizing not only the user's biometric information but also their emotional state and incorporating this information into the feedback.

[1731] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting biometric information when the user speaks using a sensor; means for recognizing emotional data when the user speaks using the sensor; means for transmitting the collected biometric information and emotional data to the server; means for analyzing the collected biometric information and emotional data using a generative AI model and identifying areas for improvement in the speech; means for generating specific advice and ideal speech samples based on the analysis results; and means for providing the advice and ideal speech samples transmitted from the server to the user on the terminal. This enables personalized training that takes the user's emotional state into consideration.

[1732] ---

[1733] A "sensor" is a device that collects biometric information and emotional data when a user speaks.

[1734] The "server" is an entity that analyzes the collected biometric information and emotional data, generates feedback, and sends it to the terminal.

[1735] A "generative AI model" is an algorithm that analyzes collected data, identifies areas for improvement in vocalization, and generates specific advice and samples of ideal vocalizations.

[1736] "Biometric information" refers to breathing patterns, voice frequencies and muscle movements acquired when the user speaks.

[1737] "Emotion data" is data that indicates the emotional state of the user that can be inferred from the tone of the user's voice and biological information.

[1738] A "terminal" is a device used by a user that receives and displays feedback provided by a server.

[1739] "Advice" refers to specific instructions or suggestions that the generative AI model gives to the user to improve their speech based on the analysis results.

[1740] "Ideal speech samples" refer to the best speech examples created by the generative AI model for users to refer to.

[1741] ---

[1742] This invention relates to a voice training system that utilizes sensors, terminals, a server, a generative AI model, and an emotion engine. The system aims to realize more personalized training by recognizing not only the user's biometric information when speaking but also the user's emotions and providing feedback.

[1743] System Overview

[1744] 1. Launching the application

[1745] A user launches a voice training app on their smartphone or tablet. When the application is launched, the device begins the initialization process for the sensors and emotion engine. The message displayed is "Preparing sensors and emotion engine."

[1746] 2. Sensor data collection

[1747] When a user selects training mode and starts speaking, sensors collect biometric information from the user. For example, a microphone captures the voice, a breathing pattern sensor measures the rhythm and depth of breathing, and an electromyography sensor detects muscle movement. The device integrates this data and stores it in memory in real time.

[1748] 3. Collecting Emotional Data

[1749] The device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state, and the recognized emotional data is also stored on the device in real time.

[1750] 4. Data transmission

[1751] The device transmits the collected biometric and emotional data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[1752] 5. AI-based data analysis

[1753] Based on the data received by the server, a detailed analysis is performed using a generative AI model. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account and adjusts the feedback content. Specifically, the AI ​​analyzes the data and returns the analysis results to the server.

[1754] 6. Generate feedback

[1755] The server generates feedback to provide to the user based on the analysis results. The generative AI model generates sample speech of ideal pronunciation along with specific advice. The content of the advice is also adjusted based on the emotional data recognized by the emotion engine.

[1756] 7. Providing Feedback

[1757] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[1758] The specific hardware, software, and generative AI models used

[1759] Hardware:

[1760] Microphone: Used to capture audio data.

[1761] Breathing pattern sensor: Measures the rhythm and depth of the user's breathing.

[1762] Myoelectric sensor: Detects muscle movement.

[1763] Smartphone or tablet: A device on which the application runs.

[1764] software:

[1765] Voice training application: Interacts with the user.

[1766] Emotion engine: Recognizes emotions by analyzing the user's tone of voice and biometric information.

[1767] Server software: Uses generative AI models to analyze data and generate feedback.

[1768] Examples of concrete examples and prompts

[1769] Specific examples

[1770] The user taps the voice training app on their smartphone's home screen to launch it. The first time the app is launched, pairing with the sensor device is required. Once pairing is complete, the app displays the message "Preparing the sensor and emotion engine." When the user selects training mode and begins speaking, the sensor collects breathing patterns, vocal frequency, and muscle movements in real time. The collected data is temporarily stored in the device's memory. While speaking, the emotion engine analyzes the user's voice and biometric information to recognize their emotions in real time. This data is sent from the device to the server. The server uses a generative AI to analyze the received data, identifying pitch variations, duration fluctuations, breathing irregularities, and other factors to identify areas for improvement in the voice. It also analyzes emotion data and personalizes the feedback. Based on the analysis results, the server generates feedback to provide to the user and creates a sample voice of the ideal voice. The device receives the feedback sent from the server and presents it to the user on the app interface. The user then reviews detailed advice and sample voices of the ideal voice, and receives personalized advice based on the emotion data.

[1771] Prompt Sentence Examples

[1772] "How do I launch the Voice Training app on my smartphone and complete the sensor pairing?"

[1773] "While making the speech, explain how the sensor collects the data."

[1774] "Please explain in detail how the emotion engine recognizes and collects the user's emotions while speaking."

[1775] The above is a description of the mode for carrying out the invention. This allows users to receive scientifically and individually optimized voice training that was not possible with conventional methods. By combining it with an emotion engine, flexible training that takes into account the user's psychological state is realized.

[1776] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1777] Step 1:

[1778] The user launches the application

[1779] A user launches a voice training app on their smartphone or tablet. When the app launches, the device begins the initialization process for the sensors and emotion engine.

[1780] Input: Tap the app icon

[1781] Output: The sensor and emotion engine initialization is complete and the message "Preparing the sensor and emotion engine" is displayed to the user.

[1782] Step 2:

[1783] Sensor data collection

[1784] When a user selects training mode and starts speaking, sensors collect biometric information from the user's speech, including breathing patterns, voice frequency, and muscle movements. The device integrates this data and stores it in memory in real time.

[1785] Input: User's speech data

[1786] Output: Breathing patterns, voice frequency, and muscle movement data are stored in the device's memory.

[1787] Step 3:

[1788] Collecting Emotional Data

[1789] While speaking, the device's built-in emotion engine analyzes the user's tone of voice and biometric information to recognize their emotional state. The recognized emotional data is also stored in memory in real time.

[1790] Input: User's voice tone, biometric information

[1791] Output: The user's emotion data is stored in the device's memory.

[1792] Step 4:

[1793] Sending data

[1794] The device transmits the collected biometric and emotional data to the server using a secure communication protocol (HTTPS).

[1795] Input: User breathing patterns, voice frequency, muscle movements, emotional data

[1796] Output: Data is sent to the server.

[1797] Step 5:

[1798] AI-powered data analysis

[1799] The server then uses a generative AI model to perform a detailed analysis of the received data. The AI ​​analyzes pitch fluctuations, vocal duration, breathing timing, and other factors to identify areas for improvement. It also takes emotional data into account to personalize the feedback.

[1800] Input: collected biometric information, emotional data

[1801] Output: Analysis results and feedback

[1802] Step 6:

[1803] Generate feedback

[1804] The server generates feedback to provide to the user based on the analysis results, uses a generative AI model to generate sample speech of ideal utterances, and adjusts the content of advice based on the user's emotions recognized by the emotion engine.

[1805] Input: Analysis results

[1806] Output: Specific advice and sample audio of ideal pronunciation

[1807] Step 7:

[1808] Providing Feedback

[1809] The device provides the user with feedback sent from the server, and through the application interface, the user can view detailed advice and sample voices of ideal pronunciation. Personalized advice based on emotion data is also displayed.

[1810] Input: Feedback sent by the server

[1811] Output: Display feedback to the user

[1812] The above is the processing flow of the program for this system. By including the input and output at each step and the specific operations, the operation of the entire system becomes clear.

[1813] (Application example 2)

[1814] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1815] Conventional voice training systems are limited in their effectiveness because they rely only on feedback based on the user's biometric information and are unable to consider the user's emotional state. Furthermore, there is a lack of systems that provide real-time feedback on performance in virtual worlds, making it difficult for users to improve immediately.

[1816] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting collected biometric information and emotional data to the server, means for analyzing the collected biometric information and emotional data using a generation AI and identifying areas for improvement in vocalization, and means for generating specific advice and ideal vocalization samples based on the areas for improvement. This provides personalized feedback that takes the user's emotional state into consideration, enabling effective real-time improvements in performance in the virtual world.

[1817] A "sensor" is a device for collecting biometric information when a user speaks.

[1818] "Biometric information" is data such as a user's breathing patterns, voice frequency, and muscle movements.

[1819] "Emotion data" is data obtained by analyzing the user's emotional state.

[1820] The "server" is a computer system that analyzes the collected biometric and emotional data and generates feedback.

[1821] "Generative AI" is a type of artificial intelligence that uses collected data to generate vocal improvements and ideal vocal samples.

[1822] "Analysis" refers to the process of using collected biometric and emotional data to identify areas for vocal improvement.

[1823] "Advice" refers to specific instructions for improvement provided to the user.

[1824] An "ideal speech sample" is a voice sample of the desired speech that users should aim for, created by generative AI.

[1825] "Terminal" means a device used by a user that receives and displays feedback sent from the server.

[1826] A "virtual world" is an imaginary environment or space generated by a computer system.

[1827] "Real-time feedback" refers to feedback that is provided immediately in response to a user's actions.

[1828] This invention relates to a voice training system that uses sensors, terminals, servers, generative AI, and emotional data. It recognizes the user's biometric information and emotional state when speaking, and provides personalized feedback based on that information, thereby enabling more effective training and real-time feedback in a virtual world.

[1829] System configuration

[1830] The system consists of the following hardware and software:

[1831] Sensor: A device that collects a user's breathing patterns, voice frequencies, and muscle movements

[1832] Device: The device used by the user, such as a smartphone or tablet.

[1833] Server: A computer system that analyzes collected biometric and emotional data and generates feedback.

[1834] Generative AI: Artificial intelligence that generates vocal improvements and ideal vocal samples

[1835] Emotion Engine: A software module that analyzes the user's emotional state

[1836] Implementation details

[1837] 1. User launches application:

[1838] The user launches the voice training app on their device. Pairing with the sensor device is required. When the app is launched for the first time, a message confirming connection to the sensor device is displayed.

[1839] 2. Biometric and emotional data collection:

[1840] Sensors collect the user's breathing patterns, voice frequency, and muscle movements in real time, while an emotion engine analyzes the user's voice and biometric data to recognize the user's emotional state. This data is temporarily stored on the device.

[1841] 3. Data transmission to the server:

[1842] The collected biometric and emotional data is sent from the device to a server, which then prepares the data for analysis.

[1843] 4. Data Analysis:

[1844] The server uses generative AI to analyze biometric and emotional data to identify areas for improvement in the user's vocalizations and adjusts the feedback content to take into account the perceived emotional state.

[1845] 5. Feedback Generation:

[1846] Based on the analysis results, the server generates specific advice and ideal speech samples. The generated feedback is provided in a personalized format, taking into account the user's emotional state.

[1847] 6. Providing Feedback:

[1848] The device receives the feedback sent from the server and displays it to the user, who can then play back and check detailed advice and sample voices of ideal pronunciation. Real-time feedback is also provided during performance in the virtual world.

[1849] Specific examples

[1850] For example, when a singer performs on a virtual stage, sensors capture their voice frequency and breathing patterns, and the emotion engine recognizes the user's level of tension. This data is sent to a server, and the AI ​​generates feedback such as "Your pitch is too high. Relax a bit and stabilize your pitch," and provides this feedback to the user in real time via their device.

[1851] Example of an input prompt for a generative AI model:

[1852] Prompt: Generate specific feedback to provide to the user based on the following biometric and audio data:

[1853] Biometric information: breathing pattern = [0.7], muscle movement = [1.3]

[1854] Audio data: frequency=[250 Hz], volume=[1.0]

[1855] Emotion: [Tension]

[1856] Feedback statement:

[1857] "Your pitch is too high. Relax a bit and stabilize your pitch. Try taking deep breaths and relaxing techniques."

[1858] This allows users to instantly improve their vocal technique and perform better in virtual environments.

[1859] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1860] Step 1:

[1861] The user launches the application. The user launches the voice training app on their device and pairs it with the sensor device. A connection confirmation message is displayed the first time the app is launched. The input data is the user's operation information, and the output data is the connection status with the sensor device.

[1862] Step 2:

[1863] The sensor collects biometric information when the user speaks. The sensor captures the user's breathing pattern, voice frequency, and muscle movement in real time. The collected data is temporarily stored on the device. The input data is the user's biometric information, and the output data is the collected biometric information.

[1864] Step 3:

[1865] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the collected biometric information and voice data to recognize the user's emotional state. The analysis results are saved on the device. The input data is biometric information and voice data, and the output data is emotion data.

[1866] Step 4:

[1867] The device sends the collected biometric information and emotional data to the server. The device sends the temporarily stored data to the server. The server receives these data. The input data is the biometric information and emotional data, and the output data is the data sent to the server.

[1868] Step 5:

[1869] The server analyzes the data using a generation AI. The generation AI analyzes biometric and emotional data to identify areas for improvement in the user's speech. At the same time, it takes the emotional data into account and adjusts the feedback content. The input data are biometric and emotional data, and the output data are areas for improvement and the adjusted feedback content.

[1870] Step 6:

[1871] The server generates specific advice and ideal speech samples. Using a generation AI, it generates specific advice and ideal speech sample audio to provide to the user. The input data are areas for improvement and feedback, and the output data are specific advice and ideal speech samples.

[1872] Step 7:

[1873] The terminal provides the generated feedback to the user. The terminal receives the advice and voice sample sent from the server and displays them to the user. The user can play and check the detailed advice and ideal voice sample voice. The input data is the feedback from the server, and the output data is the feedback display to the user.

[1874] Step 8:

[1875] It provides real-time feedback in the virtual world. Data is collected and analyzed again in real time during performance, and immediate feedback is given. This allows users to immediately identify areas for improvement and improve their performance. The input data is biometric and emotional data during performance, and the output data is real-time feedback.

[1876] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1877] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1878] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1879] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1880] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1881] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1882] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1883] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1884] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1885] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1886] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1887] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1888] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1889] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1890] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1891] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1892] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1893] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1894] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1895] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1896] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1897] The following is further disclosed regarding the above embodiment.

[1898] (Claim 1)

[1899] A means for collecting biometric information of a user when the sensor is speaking;

[1900] means for transmitting the collected biometric information to a server;

[1901] The server uses generated AI to analyze the collected biometric information and identify areas for improvement in vocalization;

[1902] A means for the server to generate specific advice and ideal vocalization samples based on the improvements;

[1903] a means for the terminal to provide the user with advice and ideal speech samples transmitted from the server;

[1904] A system including:

[1905] (Claim 2)

[1906] 2. The system of claim 1, wherein the biometric information during speech includes breathing patterns, voice frequency, and muscle movements.

[1907] (Claim 3)

[1908] 2. The system of claim 1, wherein the generated ideal speech sample is a voice sample created by a generative AI.

[1909] "Example 1"

[1910] (Claim 1)

[1911] A means for collecting biometric information of a user when the sensor is speaking;

[1912] a means for integrating and temporarily storing the collected biometric information on the device; and

[1913] a means for transmitting the collected biometric information from the terminal to a server via a network;

[1914] A means for the server to analyze the received biometric information using a generated AI model and identify areas for improvement in vocalization;

[1915] A means for the server to generate specific advice and ideal vocalization samples based on the improvements;

[1916] a means for the terminal to display the advice and the ideal speech sample sent from the server;

[1917] A system including:

[1918] (Claim 2)

[1919] 2. The system of claim 1, wherein the biometric information during speech includes breathing patterns, voice frequency, and muscle movements.

[1920] (Claim 3)

[1921] 2. The system of claim 1, wherein the generated ideal speech samples are speech samples created by a generative AI model.

[1922] "Application Example 1"

[1923] (Claim 1)

[1924] A means for collecting biometric information of a user when the sensor is speaking;

[1925] means for transmitting the collected biometric information to a server;

[1926] The server uses generated AI to analyze the collected biometric information and identify areas for improvement in vocalization;

[1927] A means for the server to generate specific advice and ideal vocalization samples based on the improvements;

[1928] a means for the terminal to provide the user with advice and ideal speech samples transmitted from the server;

[1929] A means for collecting user voices in a vehicle and analyzing driving instructions and spoken voice data;

[1930] means for providing optimal voice instructions while driving based on the analyzed data;

[1931] A system including:

[1932] (Claim 2)

[1933] 2. The system of claim 1, wherein the biometric information during speech includes breathing patterns, voice frequency, and muscle movements.

[1934] (Claim 3)

[1935] 2. The system of claim 1, wherein the generated ideal speech sample is a voice sample created by a generative AI.

[1936] "Example 2: Combining Emotion Engines"

[1937] ---

[1938] (Claim 1)

[1939] A means for collecting biometric information of a user when the sensor is speaking;

[1940] A means for a sensor to recognize emotional data when a user speaks;

[1941] means for transmitting the collected biometric information and emotion data to a server;

[1942] A means for the server to analyze the collected biometric and emotional data using a generative AI model to identify areas for improvement in vocalization;

[1943] A means for the server to generate specific advice and ideal vocalization samples based on the analysis results;

[1944] a means for the terminal to provide the user with advice and ideal speech samples transmitted from the server;

[1945] A system including:

[1946] (Claim 2)

[1947] 2. The system of claim 1, wherein the biometric information during speech includes breathing patterns, voice frequency, and muscle movements, and the recognized emotion data includes tone of voice and emotions inferred from the biometric information.

[1948] (Claim 3)

[1949] 2. The system of claim 1, wherein the generated ideal speech samples are speech samples created by a generative AI model.

[1950] ---

[1951] "Application example 2 when combining emotion engines"

[1952] (Claim 1)

[1953] A means for collecting biometric information of a user when the sensor is speaking;

[1954] means for transmitting the collected biometric information and emotion data to a server;

[1955] The server uses generated AI to analyze the collected biometric information and emotional data and identify areas for improvement in vocalization;

[1956] A means for the server to generate specific advice and ideal vocalization samples based on the improvements;

[1957] a means for the terminal to provide the user with advice and ideal speech samples transmitted from the server;

[1958] a means of providing real-time feedback on performance in the virtual world;

[1959] A system including:

[1960] (Claim 2)

[1961] 2. The system of claim 1, wherein the biometric information during speech includes breathing patterns, voice frequency, and muscle movements.

[1962] (Claim 3)

[1963] 2. The system of claim 1, wherein the generated ideal speech sample is a voice sample created by a generative AI. [Explanation of symbols]

[1964] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting biometric information of a user when the sensor is speaking; means for transmitting the collected biometric information to a server; The server uses generated AI to analyze the collected biometric information and identify areas for improvement in vocalization; A means for the server to generate specific advice and ideal vocalization samples based on the improvements; a means for the terminal to provide the user with advice and ideal speech samples transmitted from the server; A system including:

2. The system of claim 1 , wherein the biometric information during speech includes breathing patterns, voice frequencies, and muscle movements.

3. 2. The system of claim 1, wherein the generated ideal speech samples are voice samples created by a generation AI.

Images