system

Abstract

The system according to this embodiment aims to enable users with poor articulation to communicate effectively using their own voice. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, a provision unit, and a training unit. The collection unit collects the user's voice. The analysis unit analyzes the voice collected by the collection unit and trains the generation AI. The generation unit performs reading aloud or transcription in its own voice based on the data analyzed by the analysis unit. The provision unit provides the voice and transcription generated by the generation unit to the user. The training unit performs articulation improvement training based on the data generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult for users with poor fluency to communicate effectively using their own voices.

[0005] The system according to the embodiment aims to enable users with poor fluency to communicate effectively using their own voices.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a provision unit, and a training unit. The collection unit collects the user's voice. The analysis unit analyzes the voice collected by the collection unit and uses it to train the generation AI. The generation unit performs reading aloud or transcription in its own voice based on the data analyzed by the analysis unit. The provision unit provides the audio and transcription generated by the generation unit to the user. The training unit performs articulation improvement training based on the data generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment allows users with poor articulation to communicate effectively using their own voice. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The articulation support system according to an embodiment of the present invention is a system that provides articulation support using a generative AI. This articulation support system collects the user's voice and repeatedly analyzes and learns it using the generative AI. Next, the generative AI reads aloud in the user's voice and creates a dedicated transcript. Furthermore, the generative AI creates a script that matches the user's articulation and provides articulation improvement training. This mechanism aims to create a world where people do not have to worry about articulation. For example, when a user says "Let's have a meeting at 7 o'clock," the audio is collected. Next, the generative AI analyzes the collected audio and learns the user's voice. The generative AI reproduces the user's voice and reads the input text in the user's voice. For example, when a user inputs "Let's have a meeting at 7 o'clock," the generative AI reads the text in the user's voice and generates easy-to-understand audio. Furthermore, the generative AI analyzes the user's voice and creates a dedicated transcript. It converts what the user says into text in real time and also handles pronunciations that are difficult to understand. For example, when a user says "Let's have a meeting at 7 o'clock," the generative AI analyzes the audio and creates an accurate transcript. Furthermore, the generating AI analyzes the user's articulation and selects easy-to-pronounce words to create a script. When the user is giving a presentation or speech, the generating AI selects the most suitable words and creates a script. For example, if the user has difficulty saying "Let's have a meeting at 7 o'clock," the generating AI will change it to an easier-to-pronounce phrase such as "Let's have a meeting at 7 o'clock." Finally, the generating AI evaluates the user's pronunciation and provides training to improve articulation. It analyzes what the user has said, determines which parts are easy to understand and which are difficult to understand, and provides feedback on areas for improvement. For example, if the user says "Let's have a meeting at 7 o'clock," the generating AI will determine that the pronunciation of "7 o'clock" is difficult to understand and suggest ways to practice pronunciation. In this way, the articulation support system can improve the user's articulation and provide more natural and easy-to-understand audio.

[0029] The articulation support system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a provision unit, and a training unit. The collection unit collects the user's voice. For example, if the user says, "Let's have a meeting at 7 o'clock," the collection unit collects that voice. The collection unit can use noise cancellation technology to collect the user's voice in high quality. The analysis unit analyzes the voice collected by the collection unit and trains the generation AI. For example, the analysis unit performs frequency analysis on the collected voice and extracts the user's voice tone and pronunciation characteristics. The analysis unit provides data to the generation AI for training on the user's voice tone and pronunciation characteristics. The generation unit performs reading aloud or transcription in its own voice tone based on the data analyzed by the analysis unit. For example, if the user inputs, "Let's have a meeting at 7 o'clock," the generation AI reads the text aloud in the user's voice tone and generates easy-to-understand audio. The generation unit can use speech synthesis technology to reproduce the user's voice tone. The provisioning unit provides the user with the audio and transcript generated by the generation unit. For example, the provisioning unit sends the generated audio to the user's smartphone or personal computer. The provisioning unit can also send the generated transcript to the user's email address. The training unit conducts speech improvement training based on the data generated by the generation unit. For example, when the user says, "Let's have a meeting at 7 o'clock," the generation AI determines that the pronunciation of "7 o'clock" is difficult to understand and suggests methods for pronunciation practice. The training unit evaluates the user's pronunciation and provides feedback on areas for improvement. As a result, the speech support system according to this embodiment can improve the user's speech and provide more natural and easy-to-understand audio.

[0030] The collection unit collects the user's voice. For example, if a user says, "Let's have a meeting at 7 o'clock," the collection unit will collect that voice. The collection unit can use noise cancellation technology to collect the user's voice in high quality. Specifically, the collection unit uses a high-sensitivity microphone and implements an advanced noise cancellation algorithm to reduce ambient noise. This algorithm analyzes ambient sounds in real time and can clearly collect only the user's voice. Furthermore, the collection unit sets a high sampling rate for the voice, allowing it to accurately capture subtle nuances and intonation. As a result, the collected voice data can maintain high accuracy during processing in the analysis and generation units. The collection unit is also designed to temporarily store the user's voice data, allowing for playback and re-analysis as needed. This allows users to compare their progress with past voice data when practicing pronunciation. To protect user privacy, the collection unit encrypts the voice data and controls access to ensure data security. As a result, the collection unit can collect the user's voice in high quality and securely, improving the overall system performance.

[0031] The analysis unit analyzes the voice collected by the collection unit and uses this analysis to train the generation AI. For example, the analysis unit performs frequency analysis on the collected audio to extract the user's voice tone and pronunciation characteristics. Specifically, the analysis unit converts the audio signal into the frequency domain using methods such as Fourier transform and Mel-frequency cepstrum coefficients (MFCC) to analyze the audio features in detail. This allows for the extraction of characteristics such as the user's voice pitch, volume, rhythm, and intonation. Furthermore, the analysis unit uses speech recognition technology to evaluate the accuracy and fluency of the user's pronunciation. For example, it calculates the degree of pronunciation agreement at the phoneme level to evaluate how well the user's pronunciation matches standard pronunciation. The analysis unit provides these analysis results to the generation AI, which uses them as data for the generation AI to learn the user's voice tone and pronunciation characteristics. The analysis unit can analyze audio data in real time and provide the generation AI with the latest data each time the user speaks. This allows the generation AI to continuously learn from changes and improvements in the user's pronunciation, enabling it to generate more natural and easy-to-understand audio. The analysis unit also has a function to compare past and current audio data and evaluate the user's pronunciation progress. This allows users to check their progress in improving their pronunciation and set further training goals.

[0032] The generation unit performs voice-over and transcription in its own voice based on data analyzed by the analysis unit. For example, if a user inputs "Let's have a meeting at 7 o'clock," the generation AI will read the text in the user's voice, producing easy-to-understand audio. The generation unit can use speech synthesis technology to reproduce the user's voice. Specifically, the generation unit uses a deep learning-based speech synthesis model to faithfully reproduce the user's voice and pronunciation characteristics. Based on the speech feature data provided by the analysis unit, the generation AI mimics the user's voice and generates audio with natural intonation and rhythm. When converting text input by the user into speech, the generation unit can consider the context and meaning, adding appropriate intonation and emphasis. As a result, the generated audio is not merely mechanical, but natural and easy to understand. The generation unit can provide the generated audio to the user in real time, allowing the user to immediately check the improvement in their pronunciation. The generation unit also has a function to save the generated audio, allowing for later playback and comparison. This allows users to track changes in their pronunciation over the long term and see the effectiveness of their training.

[0033] The service provider delivers the audio and transcripts generated by the generation unit to the user. For example, the service provider can send the generated audio to the user's smartphone or personal computer. The service provider can also send the generated transcript to the user's email address. Specifically, the service provider can stream the generated audio data to the user's device for real-time playback. The service provider can also save the generated transcript as a text file for later reference. The service provider can support multiple devices and platforms, taking user convenience into consideration. For example, it can make the generated audio and transcripts easily accessible through smartphone apps and web browsers. Furthermore, the service provider can collect user feedback and continuously improve the quality of the generated audio and transcripts. For example, users can evaluate the clarity and naturalness of the generated audio, and the parameters of the generation AI can be adjusted based on the evaluation results. This allows the service provider to provide users with high-quality audio and transcripts and improve the overall user experience of the system.

[0034] The training unit provides speech improvement training based on data generated by the generation unit. For example, if a user says, "Let's have a meeting at 7 o'clock," the generation AI will determine that the pronunciation of "7 o'clock" is unclear and suggest methods for pronunciation practice. Specifically, the training unit has an algorithm to evaluate the user's pronunciation and provide feedback on areas for improvement. For example, it analyzes the user's pronunciation at the phoneme level and, if a particular phoneme is not pronounced correctly, suggests methods for practicing that phoneme. The training unit provides the user with specific pronunciation practice instructions, such as practicing repeating a particular phoneme or teaching how to adjust tongue position and mouth shape. Furthermore, the training unit evaluates the user's pronunciation progress in real time and provides feedback on the effectiveness of the practice. This allows the user to see how much their pronunciation has improved and set further practice goals. The training unit can also accumulate the user's pronunciation data and provide long-term training plans. This allows the user to continuously work on improving their pronunciation and ultimately achieve more natural and easily understandable speech.

[0035] The data collection unit can analyze the user's past voice data and select the optimal collection method. For example, the data collection unit can select the collection method that yields the clearest audio based on the audio data the user has collected in the past. The data collection unit can also analyze the user's past voice data to determine that the optimal audio can be obtained by collecting it at a specific time of day. The data collection unit can also determine that the optimal audio can be obtained by using a specific device based on the user's past voice data. In this way, clear audio can be collected by selecting the optimal collection method based on past voice data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past voice data into a generating AI and have the generating AI select the optimal collection method.

[0036] The voice collection unit can filter out the user's current ambient sounds to remove noise when collecting voice. For example, if the user is talking in a cafe, the voice collection unit can filter out background noise. If the user is talking while out, the voice collection unit can also filter out wind noise and car noise. If the user is talking at home, the voice collection unit can also filter out sounds from household appliances and television. This improves the quality of the collected voice by filtering out ambient sounds and removing noise. Filtering ambient sounds can be achieved using technologies such as noise cancellation technology and filtering algorithms. Some or all of the above processing in the voice collection unit may be performed using AI, for example, or without AI. For example, the voice collection unit can input the user's ambient sound data into a generating AI and have the generating AI perform noise reduction.

[0037] The collection unit can prioritize the collection of highly relevant audio by considering the user's geographical location information when collecting voices. For example, if the user is in a specific region, the collection unit can collect audio considering the dialect and accent of that region. If the user is traveling, the collection unit can also prioritize the collection of audio related to the language and culture of the travel destination. If the user is at work, the collection unit can also prioritize the collection of workplace conversations and technical terms. By considering geographical location information when collecting audio, highly relevant audio can be collected. Consideration of geographical location information can be achieved using technologies such as GPS data and IP addresses. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant audio.

[0038] The collection unit can analyze the user's social media activity and collect relevant audio when collecting voices. For example, the collection unit can collect phrases and words that the user frequently uses on social media. The collection unit can also collect relevant audio from videos and audio shared by the user on social media. The collection unit can also determine the optimal collection timing based on the user's activity times on social media. This allows for efficient collection of user-related audio by analyzing social media activity and collecting audio. The analysis of social media activity is based on data such as post content, the number of likes, and comments. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's social media data into a generating AI and have the generating AI perform the collection of relevant audio.

[0039] The analysis unit can identify articulation problems by analyzing the frequency characteristics of the voice in detail during the analysis. For example, the analysis unit can analyze the high-frequency components of the user's voice to identify articulation problems. The analysis unit can also analyze the low-frequency components of the user's voice to identify articulation problems. The analysis unit can also analyze the mid-frequency components of the user's voice to identify articulation problems. In this way, articulation problems can be accurately identified by analyzing the frequency characteristics of the voice. Frequency characteristic analysis is achieved using techniques such as spectral analysis and formant analysis. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input the user's voice data into the generative AI and have the generative AI perform the frequency characteristic analysis.

[0040] The analysis unit can learn the user's pronunciation patterns during analysis and reflect individual pronunciation characteristics. For example, the analysis unit can learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific phonemes. The analysis unit can also learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific phrases. The analysis unit can also learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific accents. This makes it possible to perform analysis that reflects individual pronunciation characteristics by learning pronunciation patterns. Learning pronunciation patterns is achieved using techniques such as phoneme analysis and pronunciation timing. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input the user's pronunciation data into the generative AI and have the generative AI perform pronunciation pattern learning.

[0041] The analysis unit can improve the accuracy of its analysis by referring to the user's past pronunciation data during the analysis process. For example, the analysis unit can improve the accuracy of analyzing specific phonemes based on the user's past pronunciation data. The analysis unit can also improve the accuracy of analyzing specific phrases based on the user's past pronunciation data. The analysis unit can also improve the accuracy of analyzing specific accents based on the user's past pronunciation data. In this way, the accuracy of the analysis is improved by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the user's past pronunciation data into the generation AI and have the generation AI perform the analysis accuracy improvement.

[0042] The analysis unit can improve the accuracy of its analysis by referring to literature data related to the user's pronunciation during the analysis process. For example, the analysis unit can improve the accuracy of its analysis by referring to academic papers related to the user's pronunciation. The analysis unit can also improve the accuracy of its analysis by referring to specialized books related to the user's pronunciation. The analysis unit can also improve the accuracy of its analysis by referring to online resources related to the user's pronunciation. In this way, the accuracy of the analysis is improved by referring to literature data. The reference to literature data is based on data such as academic papers and technical reports. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input literature data related to the user's pronunciation into the generation AI and have the generation AI perform the analysis accuracy improvement.

[0043] The generation unit can generate speech that reflects the user's pronunciation characteristics during the generation process. For example, the generation unit can generate speech that reflects the pronunciation characteristics of specific phonemes used by the user. The generation unit can also generate speech that reflects the pronunciation characteristics of specific phrases used by the user. The generation unit can also generate speech that reflects the pronunciation characteristics of specific accents used by the user. By generating speech that reflects pronunciation characteristics, it is possible to provide the user with natural-sounding speech. Reflection of pronunciation characteristics is achieved, for example, through techniques such as phoneme emphasis and intonation adjustment. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit can input the user's pronunciation data into the generation AI and have the generation AI perform the reflection of pronunciation characteristics.

[0044] The generation unit can generate natural-sounding speech by taking into account the user's pronunciation habits during generation. For example, the generation unit can generate speech by taking into account the user's pronunciation habits for specific phonemes. The generation unit can also generate speech by taking into account the user's pronunciation habits for specific phrases. The generation unit can also generate speech by taking into account the user's pronunciation habits for specific accents. This allows for the generation of more natural-sounding speech by taking into account pronunciation habits. Consideration of pronunciation habits is achieved, for example, through techniques such as the method of pronouncing specific sounds and rhythmic patterns. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's pronunciation data into the generation AI and have the generation AI perform the consideration of pronunciation habits.

[0045] The generation unit can improve the accuracy of generation by referring to the user's past pronunciation data during generation. For example, the generation unit can improve the accuracy of generating specific phonemes based on the user's past pronunciation data. The generation unit can also improve the accuracy of generating specific phrases based on the user's past pronunciation data. The generation unit can also improve the accuracy of generating specific accents based on the user's past pronunciation data. In this way, the accuracy of generation is improved by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past pronunciation data into the generation AI and have the generation AI perform the generation accuracy improvement.

[0046] The generation unit can improve the accuracy of its generation by referring to literature data related to the user's pronunciation during the generation process. For example, the generation unit can refer to academic papers related to the user's pronunciation to improve the accuracy of its generation. It can also refer to specialized books related to the user's pronunciation to improve the accuracy of its generation. It can also refer to online resources related to the user's pronunciation to improve the accuracy of its generation. This improves the accuracy of the generation by referring to literature data. The reference to literature data is based on data such as academic papers and technical reports. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input literature data related to the user's pronunciation into the generation AI and have the generation AI perform the generation accuracy improvement.

[0047] The service provider can select the optimal service delivery method by referring to the user's past usage history at the time of delivery. For example, the service provider can select the optimal method based on the service delivery method the user has used in the past. The service provider can also select the optimal service delivery method for a specific time period based on the user's past usage history. The service provider can also select the service delivery method for a specific device based on the user's past usage history. In this way, the optimal service delivery method can be selected by referring to past usage history. The referencing of past usage history is done based on data such as the functions used and usage time. Some or all of the above processing in the service provider is performed using a generation AI. For example, the service provider can input the user's past usage history into the generation AI and have the generation AI select the optimal service delivery method.

[0048] The delivery unit can select the optimal delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the delivery unit will select a delivery method that matches the screen size. If the user is using a tablet, the delivery unit can also select a delivery method optimized for a larger screen. If the user is using a smartwatch, the delivery unit can also select a concise and highly visible delivery method. In this way, the optimal delivery method can be selected by considering device information. This consideration of device information is based on data such as the device type and OS version. Some or all of the above processing in the delivery unit is performed using a generation AI. For example, the delivery unit can input the user's device information into the generation AI and have the generation AI select the optimal delivery method.

[0049] The training unit can select the optimal training method by referring to the user's past pronunciation data during training. For example, the training unit can select a training method for a specific phoneme based on the user's past pronunciation data. The training unit can also select a training method for a specific phrase based on the user's past pronunciation data. The training unit can also select a training method for a specific accent based on the user's past pronunciation data. In this way, the optimal training method can be selected by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the training unit is performed using a generative AI. For example, the training unit can input the user's past pronunciation data into the generative AI and have the generative AI select the optimal training method.

[0050] The training unit can create individualized training plans during training, taking into account the user's pronunciation habits. For example, the training unit can create a training plan considering the user's pronunciation habits for specific phonemes. The training unit can also create a training plan considering the user's pronunciation habits for specific phrases. The training unit can also create a training plan considering the user's pronunciation habits for specific accents. This allows for the provision of individualized training plans by taking pronunciation habits into account. Consideration of pronunciation habits is achieved, for example, through techniques such as the pronunciation method of specific sounds and rhythmic patterns. Some or all of the above processing in the training unit is performed using a generative AI. For example, the training unit can input the user's pronunciation data into the generative AI and have the generative AI perform the consideration of pronunciation habits.

[0051] The training unit can select the optimal training method during training by considering the user's geographical location. For example, if the user is in a specific region, the training unit can select a training method that takes into account the local dialect and accent. If the user is traveling, the training unit can also select a training method that is relevant to the language and culture of the travel destination. If the user is at work, the training unit can also select a training method that takes into account workplace conversations and technical terms. In this way, the optimal training method can be selected by considering geographical location. Consideration of geographical location is based on data such as GPS data and IP addresses. Some or all of the above processing in the training unit is performed using generative AI. For example, the training unit can input the user's geographical location information into the generative AI and have the generative AI select the optimal training method.

[0052] The training unit can analyze a user's social media activity during training and suggest training methods. For example, the training unit can suggest training methods based on phrases and words that the user frequently uses on social media. The training unit can also suggest relevant training methods from videos and audio shared by the user on social media. The training unit can also suggest the optimal training timing based on the time of day the user is active on social media. In this way, by analyzing social media activity, the optimal training method can be suggested. The analysis of social media activity is performed based on data such as post content, the number of likes, and comments. Some or all of the above processing in the training unit is performed using generative AI. For example, the training unit can input the user's social media data into the generative AI and have the generative AI suggest training methods.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The speech articulation support system can monitor the user's health condition when collecting their voice and adjust the collection method accordingly. For example, if the user has a cold, the collection unit can take changes in voice into consideration during collection. If the user is tired, the collection unit can also collect voice efficiently in a short amount of time. Furthermore, if the user is healthy, it can collect longer audio recordings and perform detailed analysis. This allows for the collection of more accurate voice data by adjusting the collection method according to the user's health condition. Health condition monitoring can be achieved using technologies such as vital sign measurement, self-reporting, or wearable devices. Some or all of the above-described processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's health data into a generating AI and have the generating AI adjust the collection method.

[0055] The speech articulation support system can monitor the user's activity level when collecting their voice and adjust the collection method accordingly. For example, if the user is exercising, the collection unit can efficiently collect voice data in a short amount of time. If the user is resting, it can collect longer audio recordings and perform detailed analysis. Furthermore, if the user is working, the collection unit can collect voice data during breaks. By adjusting the collection method according to the user's activity level, more accurate voice data can be collected. Activity level monitoring can be achieved using technologies such as accelerometers, self-reporting, or wearable devices. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input user activity data into a generating AI and have the generating AI adjust the collection method.

[0056] The articulation support system can monitor the quality of the user's voice in real time when collecting their voice and adjust the collection method according to that quality. For example, if the user's voice is clear, it can collect a long audio recording and perform a detailed analysis. If the user's voice is hoarse, it can collect the voice efficiently in a short amount of time. Furthermore, if the user's voice is modulated, the collection unit can provide feedback to improve the voice quality. By adjusting the collection method according to the quality of the user's voice, more accurate audio data can be collected. Monitoring of voice quality is achieved using technologies such as speech analysis and frequency analysis. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's voice quality data into a generating AI and have the generating AI adjust the collection method.

[0057] The speech articulation support system can analyze the frequency characteristics of the user's voice in real time when collecting it, and can emphasize specific frequency bands during collection. For example, emphasizing the high-frequency components of the user's voice can result in clearer speech. Emphasizing the low-frequency components can result in richer speech. Furthermore, emphasizing the mid-frequency components of the user's voice can result in balanced speech. In this way, emphasizing the frequency characteristics improves the quality of the collected speech. Frequency characteristic analysis can be achieved using techniques such as spectral analysis and formant analysis. Some or all of the above processing in the collection unit may be performed using AI, or it may be performed without AI. For example, the collection unit can input the frequency data of the user's voice into a generating AI and have the generating AI perform frequency characteristic emphasis.

[0058] The speech articulation support system can monitor the volume of the user's voice in real time when collecting it and adjust the collection method according to the volume. For example, if the user's voice is loud, the collection unit can adjust the volume to collect clear audio. If the user's voice is quiet, the collection unit can also increase the sensitivity to collect audio. Furthermore, if the user's voice fluctuates, the collection unit can adjust the volume in real time to collect stable audio. This allows for the collection of more accurate audio data by adjusting the collection method according to the volume of the user's voice. Volume monitoring is achieved using technologies such as voice analysis and sound pressure level measurement. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's voice volume data into a generating AI and have the generating AI adjust the collection method.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The collection unit collects the user's voice. For example, if a user says, "Let's have a meeting at 7 o'clock," the unit collects that audio. The collection unit can collect high-quality audio using noise cancellation technology. Step 2: The analysis unit analyzes the voice collected by the collection unit and uses it to train the generation AI. For example, it performs frequency analysis on the collected voice and extracts the user's voice tone and pronunciation characteristics. The analysis unit provides the generation AI with data to train it on the user's voice tone and pronunciation characteristics. Step 3: The generation unit performs reading aloud or transcription in its own voice based on the data analyzed by the analysis unit. For example, if the user inputs "Let's have a meeting at 7 o'clock," the generation AI will read the text aloud in the user's voice, producing easy-to-understand audio. The generation unit uses speech synthesis technology to reproduce the user's voice. Step 4: The providing unit provides the user with the audio and transcript generated by the generating unit. For example, it can send the generated audio to the user's smartphone or personal computer. It can also send the generated transcript to the user's email address. Step 5: The training unit conducts speech improvement training based on the data generated by the generation unit. For example, when a user says, "Let's have a meeting at 7 o'clock," the generation AI determines that the pronunciation of "7 o'clock" is difficult to hear and suggests ways to practice pronunciation. The training unit evaluates the user's pronunciation and provides feedback on areas for improvement.

[0061] (Example of form 2) The articulation support system according to an embodiment of the present invention is a system that provides articulation support using a generative AI. This articulation support system collects the user's voice and repeatedly analyzes and learns it using the generative AI. Next, the generative AI reads aloud in the user's voice and creates a dedicated transcript. Furthermore, the generative AI creates a script that matches the user's articulation and provides articulation improvement training. This mechanism aims to create a world where people do not have to worry about articulation. For example, when a user says "Let's have a meeting at 7 o'clock," the audio is collected. Next, the generative AI analyzes the collected audio and learns the user's voice. The generative AI reproduces the user's voice and reads the input text in the user's voice. For example, when a user inputs "Let's have a meeting at 7 o'clock," the generative AI reads the text in the user's voice and generates easy-to-understand audio. Furthermore, the generative AI analyzes the user's voice and creates a dedicated transcript. It converts what the user says into text in real time and also handles pronunciations that are difficult to understand. For example, when a user says "Let's have a meeting at 7 o'clock," the generative AI analyzes the audio and creates an accurate transcript. Furthermore, the generating AI analyzes the user's articulation and selects easy-to-pronounce words to create a script. When the user is giving a presentation or speech, the generating AI selects the most suitable words and creates a script. For example, if the user has difficulty saying "Let's have a meeting at 7 o'clock," the generating AI will change it to an easier-to-pronounce phrase such as "Let's have a meeting at 7 o'clock." Finally, the generating AI evaluates the user's pronunciation and provides training to improve articulation. It analyzes what the user has said, determines which parts are easy to understand and which are difficult to understand, and provides feedback on areas for improvement. For example, if the user says "Let's have a meeting at 7 o'clock," the generating AI will determine that the pronunciation of "7 o'clock" is difficult to understand and suggest ways to practice pronunciation. In this way, the articulation support system can improve the user's articulation and provide more natural and easy-to-understand audio.

[0062] The articulation support system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a provision unit, and a training unit. The collection unit collects the user's voice. For example, if the user says, "Let's have a meeting at 7 o'clock," the collection unit collects that voice. The collection unit can use noise cancellation technology to collect the user's voice in high quality. The analysis unit analyzes the voice collected by the collection unit and trains the generation AI. For example, the analysis unit performs frequency analysis on the collected voice and extracts the user's voice tone and pronunciation characteristics. The analysis unit provides data to the generation AI for training on the user's voice tone and pronunciation characteristics. The generation unit performs reading aloud or transcription in its own voice tone based on the data analyzed by the analysis unit. For example, if the user inputs, "Let's have a meeting at 7 o'clock," the generation AI reads the text aloud in the user's voice tone and generates easy-to-understand audio. The generation unit can use speech synthesis technology to reproduce the user's voice tone. The provisioning unit provides the user with the audio and transcript generated by the generation unit. For example, the provisioning unit sends the generated audio to the user's smartphone or personal computer. The provisioning unit can also send the generated transcript to the user's email address. The training unit conducts speech improvement training based on the data generated by the generation unit. For example, when the user says, "Let's have a meeting at 7 o'clock," the generation AI determines that the pronunciation of "7 o'clock" is difficult to understand and suggests methods for pronunciation practice. The training unit evaluates the user's pronunciation and provides feedback on areas for improvement. As a result, the speech support system according to this embodiment can improve the user's speech and provide more natural and easy-to-understand audio.

[0063] The collection unit collects the user's voice. For example, if a user says, "Let's have a meeting at 7 o'clock," the collection unit will collect that voice. The collection unit can use noise cancellation technology to collect the user's voice in high quality. Specifically, the collection unit uses a high-sensitivity microphone and implements an advanced noise cancellation algorithm to reduce ambient noise. This algorithm analyzes ambient sounds in real time and can clearly collect only the user's voice. Furthermore, the collection unit sets a high sampling rate for the voice, allowing it to accurately capture subtle nuances and intonation. As a result, the collected voice data can maintain high accuracy during processing in the analysis and generation units. The collection unit is also designed to temporarily store the user's voice data, allowing for playback and re-analysis as needed. This allows users to compare their progress with past voice data when practicing pronunciation. To protect user privacy, the collection unit encrypts the voice data and controls access to ensure data security. As a result, the collection unit can collect the user's voice in high quality and securely, improving the overall system performance.

[0064] The analysis unit analyzes the voice collected by the collection unit and uses this analysis to train the generation AI. For example, the analysis unit performs frequency analysis on the collected audio to extract the user's voice tone and pronunciation characteristics. Specifically, the analysis unit converts the audio signal into the frequency domain using methods such as Fourier transform and Mel-frequency cepstrum coefficients (MFCC) to analyze the audio features in detail. This allows for the extraction of characteristics such as the user's voice pitch, volume, rhythm, and intonation. Furthermore, the analysis unit uses speech recognition technology to evaluate the accuracy and fluency of the user's pronunciation. For example, it calculates the degree of pronunciation agreement at the phoneme level to evaluate how well the user's pronunciation matches standard pronunciation. The analysis unit provides these analysis results to the generation AI, which uses them as data for the generation AI to learn the user's voice tone and pronunciation characteristics. The analysis unit can analyze audio data in real time and provide the generation AI with the latest data each time the user speaks. This allows the generation AI to continuously learn from changes and improvements in the user's pronunciation, enabling it to generate more natural and easy-to-understand audio. The analysis unit also has a function to compare past and current audio data and evaluate the user's pronunciation progress. This allows users to check their progress in improving their pronunciation and set further training goals.

[0065] The generation unit performs voice-over and transcription in its own voice based on data analyzed by the analysis unit. For example, if a user inputs "Let's have a meeting at 7 o'clock," the generation AI will read the text in the user's voice, producing easy-to-understand audio. The generation unit can use speech synthesis technology to reproduce the user's voice. Specifically, the generation unit uses a deep learning-based speech synthesis model to faithfully reproduce the user's voice and pronunciation characteristics. Based on the speech feature data provided by the analysis unit, the generation AI mimics the user's voice and generates audio with natural intonation and rhythm. When converting text input by the user into speech, the generation unit can consider the context and meaning, adding appropriate intonation and emphasis. As a result, the generated audio is not merely mechanical, but natural and easy to understand. The generation unit can provide the generated audio to the user in real time, allowing the user to immediately check the improvement in their pronunciation. The generation unit also has a function to save the generated audio, allowing for later playback and comparison. This allows users to track changes in their pronunciation over the long term and see the effectiveness of their training.

[0066] The service provider delivers the audio and transcripts generated by the generation unit to the user. For example, the service provider can send the generated audio to the user's smartphone or personal computer. The service provider can also send the generated transcript to the user's email address. Specifically, the service provider can stream the generated audio data to the user's device for real-time playback. The service provider can also save the generated transcript as a text file for later reference. The service provider can support multiple devices and platforms, taking user convenience into consideration. For example, it can make the generated audio and transcripts easily accessible through smartphone apps and web browsers. Furthermore, the service provider can collect user feedback and continuously improve the quality of the generated audio and transcripts. For example, users can evaluate the clarity and naturalness of the generated audio, and the parameters of the generation AI can be adjusted based on the evaluation results. This allows the service provider to provide users with high-quality audio and transcripts and improve the overall user experience of the system.

[0067] The training unit provides speech improvement training based on data generated by the generation unit. For example, if a user says, "Let's have a meeting at 7 o'clock," the generation AI will determine that the pronunciation of "7 o'clock" is unclear and suggest methods for pronunciation practice. Specifically, the training unit has an algorithm to evaluate the user's pronunciation and provide feedback on areas for improvement. For example, it analyzes the user's pronunciation at the phoneme level and, if a particular phoneme is not pronounced correctly, suggests methods for practicing that phoneme. The training unit provides the user with specific pronunciation practice instructions, such as practicing repeating a particular phoneme or teaching how to adjust tongue position and mouth shape. Furthermore, the training unit evaluates the user's pronunciation progress in real time and provides feedback on the effectiveness of the practice. This allows the user to see how much their pronunciation has improved and set further practice goals. The training unit can also accumulate the user's pronunciation data and provide long-term training plans. This allows the user to continuously work on improving their pronunciation and ultimately achieve more natural and easily understandable speech.

[0068] The collection unit can estimate the user's emotions and adjust the timing of voice collection based on the estimated emotions. For example, if the user is relaxed, the collection unit can collect voice during natural conversation. If the user is tense, the collection unit can provide a relaxing environment before collecting voice. If the user is in a hurry, the collection unit can collect voice efficiently in a short amount of time. By adjusting the timing of voice collection according to the user's emotions, more natural voice can be collected. Emotion estimation is achieved using technologies such as voice analysis, facial expression analysis, and text analysis. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's voice data into a generating AI and have the generating AI perform emotion estimation.

[0069] The data collection unit can analyze the user's past voice data and select the optimal collection method. For example, the data collection unit can select the collection method that yields the clearest audio based on the audio data the user has collected in the past. The data collection unit can also analyze the user's past voice data to determine that the optimal audio can be obtained by collecting it at a specific time of day. The data collection unit can also determine that the optimal audio can be obtained by using a specific device based on the user's past voice data. In this way, clear audio can be collected by selecting the optimal collection method based on past voice data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past voice data into a generating AI and have the generating AI select the optimal collection method.

[0070] The voice collection unit can filter out the user's current ambient sounds to remove noise when collecting voice. For example, if the user is talking in a cafe, the voice collection unit can filter out background noise. If the user is talking while out, the voice collection unit can also filter out wind noise and car noise. If the user is talking at home, the voice collection unit can also filter out sounds from household appliances and television. This improves the quality of the collected voice by filtering out ambient sounds and removing noise. Filtering ambient sounds can be achieved using technologies such as noise cancellation technology and filtering algorithms. Some or all of the above processing in the voice collection unit may be performed using AI, for example, or without AI. For example, the voice collection unit can input the user's ambient sound data into a generating AI and have the generating AI perform noise reduction.

[0071] The collection unit can estimate the user's emotions and determine the priority of the voices to collect based on the estimated emotions. For example, if the user is relaxed, the collection unit may prioritize collecting longer voices. If the user is tense, the collection unit may also prioritize collecting shorter voices. If the user is in a hurry, the collection unit may also prioritize collecting important phrases. This allows for the priority collection of important voices by determining the priority of the voices to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using AI, or not using AI. For example, the collection unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0072] The collection unit can prioritize the collection of highly relevant audio by considering the user's geographical location information when collecting voices. For example, if the user is in a specific region, the collection unit can collect audio considering the dialect and accent of that region. If the user is traveling, the collection unit can also prioritize the collection of audio related to the language and culture of the travel destination. If the user is at work, the collection unit can also prioritize the collection of workplace conversations and technical terms. By considering geographical location information when collecting audio, highly relevant audio can be collected. Consideration of geographical location information can be achieved using technologies such as GPS data and IP addresses. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant audio.

[0073] The collection unit can analyze the user's social media activity and collect relevant audio when collecting voices. For example, the collection unit can collect phrases and words that the user frequently uses on social media. The collection unit can also collect relevant audio from videos and audio shared by the user on social media. The collection unit can also determine the optimal collection timing based on the user's activity times on social media. This allows for efficient collection of user-related audio by analyzing social media activity and collecting audio. The analysis of social media activity is based on data such as post content, the number of likes, and comments. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's social media data into a generating AI and have the generating AI perform the collection of relevant audio.

[0074] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis to improve accuracy. If the user is tense, the analysis unit can also perform a simplified analysis and provide results quickly. If the user is in a hurry, the analysis unit can prioritize the analysis of important parts. This allows for more accurate analysis results by adjusting the accuracy of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0075] The analysis unit can identify articulation problems by analyzing the frequency characteristics of the voice in detail during the analysis. For example, the analysis unit can analyze the high-frequency components of the user's voice to identify articulation problems. The analysis unit can also analyze the low-frequency components of the user's voice to identify articulation problems. The analysis unit can also analyze the mid-frequency components of the user's voice to identify articulation problems. In this way, articulation problems can be accurately identified by analyzing the frequency characteristics of the voice. Frequency characteristic analysis is achieved using techniques such as spectral analysis and formant analysis. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input the user's voice data into the generative AI and have the generative AI perform the frequency characteristic analysis.

[0076] The analysis unit can learn the user's pronunciation patterns during analysis and reflect individual pronunciation characteristics. For example, the analysis unit can learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific phonemes. The analysis unit can also learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific phrases. The analysis unit can also learn the user's pronunciation patterns and reflect the pronunciation characteristics of specific accents. This makes it possible to perform analysis that reflects individual pronunciation characteristics by learning pronunciation patterns. Learning pronunciation patterns is achieved using techniques such as phoneme analysis and pronunciation timing. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input the user's pronunciation data into the generative AI and have the generative AI perform pronunciation pattern learning.

[0077] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can display detailed analysis results. If the user is tense, the analysis unit can also display concise analysis results. If the user is in a hurry, the analysis unit can also display concise analysis results. By adjusting how the analysis results are displayed according to the user's emotions, the system can provide results that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit are performed using generative AI. For example, the analysis unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0078] The analysis unit can improve the accuracy of its analysis by referring to the user's past pronunciation data during the analysis process. For example, the analysis unit can improve the accuracy of analyzing specific phonemes based on the user's past pronunciation data. The analysis unit can also improve the accuracy of analyzing specific phrases based on the user's past pronunciation data. The analysis unit can also improve the accuracy of analyzing specific accents based on the user's past pronunciation data. In this way, the accuracy of the analysis is improved by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the user's past pronunciation data into the generation AI and have the generation AI perform the analysis accuracy improvement.

[0079] The analysis unit can improve the accuracy of its analysis by referring to literature data related to the user's pronunciation during the analysis process. For example, the analysis unit can improve the accuracy of its analysis by referring to academic papers related to the user's pronunciation. The analysis unit can also improve the accuracy of its analysis by referring to specialized books related to the user's pronunciation. The analysis unit can also improve the accuracy of its analysis by referring to online resources related to the user's pronunciation. In this way, the accuracy of the analysis is improved by referring to literature data. The reference to literature data is based on data such as academic papers and technical reports. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input literature data related to the user's pronunciation into the generation AI and have the generation AI perform the analysis accuracy improvement.

[0080] The generation unit can estimate the user's emotions and adjust the tone of the generated voice based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate voice in a calm tone. If the user is tense, the generation unit can also generate voice in a calm tone. If the user is in a hurry, the generation unit can also generate voice in a fast and clear tone. This allows for the generation of more natural-sounding voices by adjusting the tone of voice according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can input user voice data into the generation AI and have the generation AI perform emotion estimation.

[0081] The generation unit can generate speech that reflects the user's pronunciation characteristics during the generation process. For example, the generation unit can generate speech that reflects the pronunciation characteristics of specific phonemes used by the user. The generation unit can also generate speech that reflects the pronunciation characteristics of specific phrases used by the user. The generation unit can also generate speech that reflects the pronunciation characteristics of specific accents used by the user. By generating speech that reflects pronunciation characteristics, it is possible to provide the user with natural-sounding speech. Reflection of pronunciation characteristics is achieved, for example, through techniques such as phoneme emphasis and intonation adjustment. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit can input the user's pronunciation data into the generation AI and have the generation AI perform the reflection of pronunciation characteristics.

[0082] The generation unit can generate natural-sounding speech by taking into account the user's pronunciation habits during generation. For example, the generation unit can generate speech by taking into account the user's pronunciation habits for specific phonemes. The generation unit can also generate speech by taking into account the user's pronunciation habits for specific phrases. The generation unit can also generate speech by taking into account the user's pronunciation habits for specific accents. This allows for the generation of more natural-sounding speech by taking into account pronunciation habits. Consideration of pronunciation habits is achieved, for example, through techniques such as the method of pronouncing specific sounds and rhythmic patterns. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's pronunciation data into the generation AI and have the generation AI perform the consideration of pronunciation habits.

[0083] The generation unit can estimate the user's emotions and adjust the speed of the generated speech based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate speech at a slow speed. If the user is tense, the generation unit can also generate speech at a calm speed. If the user is in a hurry, the generation unit can also generate speech at a fast speed. By adjusting the speed of speech according to the user's emotions, speech can be generated at a more appropriate speed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0084] The generation unit can improve the accuracy of generation by referring to the user's past pronunciation data during generation. For example, the generation unit can improve the accuracy of generating specific phonemes based on the user's past pronunciation data. The generation unit can also improve the accuracy of generating specific phrases based on the user's past pronunciation data. The generation unit can also improve the accuracy of generating specific accents based on the user's past pronunciation data. In this way, the accuracy of generation is improved by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past pronunciation data into the generation AI and have the generation AI perform the generation accuracy improvement.

[0085] The generation unit can improve the accuracy of its generation by referring to literature data related to the user's pronunciation during the generation process. For example, the generation unit can refer to academic papers related to the user's pronunciation to improve the accuracy of its generation. It can also refer to specialized books related to the user's pronunciation to improve the accuracy of its generation. It can also refer to online resources related to the user's pronunciation to improve the accuracy of its generation. This improves the accuracy of the generation by referring to literature data. The reference to literature data is based on data such as academic papers and technical reports. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can input literature data related to the user's pronunciation into the generation AI and have the generation AI perform the generation accuracy improvement.

[0086] The service provider can estimate the user's emotions and adjust the format of the audio and transcript provided based on the estimated emotions. For example, if the user is relaxed, the service provider can provide a detailed transcript. If the user is tense, the service provider can also provide a concise transcript. If the user is in a hurry, the service provider can also provide a transcript that gets straight to the point. By adjusting the format according to the user's emotions, the service provider can provide audio and transcripts in a more appropriate format. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider is performed using generative AI. For example, the service provider can input the user's audio data into the generative AI and have the generative AI perform emotion estimation.

[0087] The service provider can select the optimal service delivery method by referring to the user's past usage history at the time of delivery. For example, the service provider can select the optimal method based on the service delivery method the user has used in the past. The service provider can also select the optimal service delivery method for a specific time period based on the user's past usage history. The service provider can also select the service delivery method for a specific device based on the user's past usage history. In this way, the optimal service delivery method can be selected by referring to past usage history. The referencing of past usage history is done based on data such as the functions used and usage time. Some or all of the above processing in the service provider is performed using a generation AI. For example, the service provider can input the user's past usage history into the generation AI and have the generation AI select the optimal service delivery method.

[0088] The service provider can estimate the user's emotions and prioritize the content to be delivered based on those emotions. For example, if the user is relaxed, the service provider may prioritize detailed content. If the user is stressed, the service provider may prioritize concise content. If the user is in a hurry, the service provider may prioritize content that gets straight to the point. This allows the service provider to prioritize important content by prioritizing it according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider is performed using generative AI. For example, the service provider can input user voice data into the generative AI and have the generative AI perform emotion estimation.

[0089] The delivery unit can select the optimal delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the delivery unit will select a delivery method that matches the screen size. If the user is using a tablet, the delivery unit can also select a delivery method optimized for a larger screen. If the user is using a smartwatch, the delivery unit can also select a concise and highly visible delivery method. In this way, the optimal delivery method can be selected by considering device information. This consideration of device information is based on data such as the device type and OS version. Some or all of the above processing in the delivery unit is performed using a generation AI. For example, the delivery unit can input the user's device information into the generation AI and have the generation AI select the optimal delivery method.

[0090] The training unit can estimate the user's emotions and adjust the training content based on those emotions. For example, if the user is relaxed, the training unit can provide detailed training content. If the user is tense, the training unit can also provide concise training content. If the user is in a hurry, the training unit can provide training content that gets straight to the point. By adjusting the training content according to the user's emotions, more effective training can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the training unit is performed using generative AI. For example, the training unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0091] The training unit can select the optimal training method by referring to the user's past pronunciation data during training. For example, the training unit can select a training method for a specific phoneme based on the user's past pronunciation data. The training unit can also select a training method for a specific phrase based on the user's past pronunciation data. The training unit can also select a training method for a specific accent based on the user's past pronunciation data. In this way, the optimal training method can be selected by referring to past pronunciation data. The reference to past pronunciation data is performed based on data such as recording data and pronunciation records. Some or all of the above processing in the training unit is performed using a generative AI. For example, the training unit can input the user's past pronunciation data into the generative AI and have the generative AI select the optimal training method.

[0092] The training unit can create individualized training plans during training, taking into account the user's pronunciation habits. For example, the training unit can create a training plan considering the user's pronunciation habits for specific phonemes. The training unit can also create a training plan considering the user's pronunciation habits for specific phrases. The training unit can also create a training plan considering the user's pronunciation habits for specific accents. This allows for the provision of individualized training plans by taking pronunciation habits into account. Consideration of pronunciation habits is achieved, for example, through techniques such as the pronunciation method of specific sounds and rhythmic patterns. Some or all of the above processing in the training unit is performed using a generative AI. For example, the training unit can input the user's pronunciation data into the generative AI and have the generative AI perform the consideration of pronunciation habits.

[0093] The training unit can estimate the user's emotions and determine training priorities based on those estimated emotions. For example, if the user is relaxed, the training unit may prioritize detailed training. If the user is tense, the training unit may prioritize concise training. If the user is in a hurry, the training unit may prioritize concise training. This allows for the prioritization of important training based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the training unit are performed using generative AI. For example, the training unit can input user voice data into the generative AI and have the generative AI perform emotion estimation.

[0094] The training unit can select the optimal training method during training by considering the user's geographical location. For example, if the user is in a specific region, the training unit can select a training method that takes into account the local dialect and accent. If the user is traveling, the training unit can also select a training method that is relevant to the language and culture of the travel destination. If the user is at work, the training unit can also select a training method that takes into account workplace conversations and technical terms. In this way, the optimal training method can be selected by considering geographical location. Consideration of geographical location is based on data such as GPS data and IP addresses. Some or all of the above processing in the training unit is performed using generative AI. For example, the training unit can input the user's geographical location information into the generative AI and have the generative AI select the optimal training method.

[0095] The training unit can analyze a user's social media activity during training and suggest training methods. For example, the training unit can suggest training methods based on phrases and words that the user frequently uses on social media. The training unit can also suggest relevant training methods from videos and audio shared by the user on social media. The training unit can also suggest the optimal training timing based on the time of day the user is active on social media. In this way, by analyzing social media activity, the optimal training method can be suggested. The analysis of social media activity is performed based on data such as post content, the number of likes, and comments. Some or all of the above processing in the training unit is performed using generative AI. For example, the training unit can input the user's social media data into the generative AI and have the generative AI suggest training methods.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The speech articulation support system can monitor the user's health condition when collecting their voice and adjust the collection method accordingly. For example, if the user has a cold, the collection unit can take changes in voice into consideration during collection. If the user is tired, the collection unit can also collect voice efficiently in a short amount of time. Furthermore, if the user is healthy, it can collect longer audio recordings and perform detailed analysis. This allows for the collection of more accurate voice data by adjusting the collection method according to the user's health condition. Health condition monitoring can be achieved using technologies such as vital sign measurement, self-reporting, or wearable devices. Some or all of the above-described processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's health data into a generating AI and have the generating AI adjust the collection method.

[0098] The articulation support system can estimate the user's emotions and adjust the content of the articulation improvement training based on those emotions. For example, if the user is relaxed, it can provide detailed training content. If the user is nervous, it can provide concise training content. Furthermore, if the user is in a hurry, it can provide training content that gets straight to the point. By adjusting the training content according to the user's emotions, it is possible to provide more effective training. Emotion estimation is achieved using technologies such as voice analysis, facial expression analysis, and text analysis. Some or all of the above processing in the training unit may be performed using AI or not. For example, the training unit can input the user's emotion data into a generating AI and have the generating AI adjust the training content.

[0099] The speech articulation support system can monitor the user's activity level when collecting their voice and adjust the collection method accordingly. For example, if the user is exercising, the collection unit can efficiently collect voice data in a short amount of time. If the user is resting, it can collect longer audio recordings and perform detailed analysis. Furthermore, if the user is working, the collection unit can collect voice data during breaks. By adjusting the collection method according to the user's activity level, more accurate voice data can be collected. Activity level monitoring can be achieved using technologies such as accelerometers, self-reporting, or wearable devices. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input user activity data into a generating AI and have the generating AI adjust the collection method.

[0100] The speech articulation support system can estimate the user's emotions and adjust the tone of the voice it generates based on those emotions. For example, if the user is relaxed, it can generate a calm tone of voice. If the user is nervous, it can also generate a calm tone of voice. Furthermore, if the user is in a hurry, it can generate a fast and clear tone of voice. This allows for the generation of more natural-sounding voices by adjusting the tone of voice according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or a generation AI. Some or all of the above-described processing in the generation unit may be performed using AI or not. For example, the generation unit can input the user's emotion data into a generation AI and have the generation AI perform the tone adjustment of the voice.

[0101] The articulation support system can monitor the quality of the user's voice in real time when collecting their voice and adjust the collection method according to that quality. For example, if the user's voice is clear, it can collect a long audio recording and perform a detailed analysis. If the user's voice is hoarse, it can collect the voice efficiently in a short amount of time. Furthermore, if the user's voice is modulated, the collection unit can provide feedback to improve the voice quality. By adjusting the collection method according to the quality of the user's voice, more accurate audio data can be collected. Monitoring of voice quality is achieved using technologies such as speech analysis and frequency analysis. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's voice quality data into a generating AI and have the generating AI adjust the collection method.

[0102] The speech articulation support system can estimate the user's emotions and adjust the format of the audio and transcript provided based on the estimated emotions. For example, if the user is relaxed, it can provide a detailed transcript. If the user is nervous, it can provide a concise transcript. Furthermore, if the user is in a hurry, it can provide a transcript that gets straight to the point. In this way, by adjusting the format according to the user's emotions, it can provide audio and transcripts in a more appropriate format. Emotion estimation is achieved, for example, using an emotion engine or a generative AI. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's emotion data into a generative AI and have the generative AI perform the adjustment of the delivery format.

[0103] The speech articulation support system can analyze the frequency characteristics of the user's voice in real time when collecting it, and can emphasize specific frequency bands during collection. For example, emphasizing the high-frequency components of the user's voice can result in clearer speech. Emphasizing the low-frequency components can result in richer speech. Furthermore, emphasizing the mid-frequency components of the user's voice can result in balanced speech. In this way, emphasizing the frequency characteristics improves the quality of the collected speech. Frequency characteristic analysis can be achieved using techniques such as spectral analysis and formant analysis. Some or all of the above processing in the collection unit may be performed using AI, or it may be performed without AI. For example, the collection unit can input the frequency data of the user's voice into a generating AI and have the generating AI perform frequency characteristic emphasis.

[0104] The speech articulation support system can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is relaxed, detailed analysis results can be displayed. If the user is nervous, concise analysis results can be displayed. Furthermore, if the user is in a hurry, the system can display analysis results that are concise and to the point. In this way, by adjusting the display method of the analysis results according to the user's emotions, the system can provide results that are easy for the user to understand. Emotion estimation is achieved, for example, using an emotion engine or a generative AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI adjust the display method of the analysis results.

[0105] The speech articulation support system can monitor the volume of the user's voice in real time when collecting it and adjust the collection method according to the volume. For example, if the user's voice is loud, the collection unit can adjust the volume to collect clear audio. If the user's voice is quiet, the collection unit can also increase the sensitivity to collect audio. Furthermore, if the user's voice fluctuates, the collection unit can adjust the volume in real time to collect stable audio. This allows for the collection of more accurate audio data by adjusting the collection method according to the volume of the user's voice. Volume monitoring is achieved using technologies such as voice analysis and sound pressure level measurement. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the user's voice volume data into a generating AI and have the generating AI adjust the collection method.

[0106] The speech articulation support system can estimate the user's emotions and prioritize training based on those emotions. For example, if the user is relaxed, detailed training can be prioritized. If the user is nervous, concise training can be prioritized. Furthermore, if the user is in a hurry, training that gets straight to the point can be prioritized. This ensures that important training is prioritized by determining training priorities according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative AI. Some or all of the processing described above in the training unit may be performed using AI or not. For example, the training unit can input the user's emotion data into a generative AI and have the generative AI determine the training priorities.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The collection unit collects the user's voice. For example, if a user says, "Let's have a meeting at 7 o'clock," the unit collects that audio. The collection unit can collect high-quality audio using noise cancellation technology. Step 2: The analysis unit analyzes the voice collected by the collection unit and uses it to train the generation AI. For example, it performs frequency analysis on the collected voice and extracts the user's voice tone and pronunciation characteristics. The analysis unit provides the generation AI with data to train it on the user's voice tone and pronunciation characteristics. Step 3: The generation unit performs reading aloud or transcription in its own voice based on the data analyzed by the analysis unit. For example, if the user inputs "Let's have a meeting at 7 o'clock," the generation AI will read the text aloud in the user's voice, producing easy-to-understand audio. The generation unit uses speech synthesis technology to reproduce the user's voice. Step 4: The providing unit provides the user with the audio and transcript generated by the generating unit. For example, it can send the generated audio to the user's smartphone or personal computer. It can also send the generated transcript to the user's email address. Step 5: The training unit conducts speech improvement training based on the data generated by the generation unit. For example, when a user says, "Let's have a meeting at 7 o'clock," the generation AI determines that the pronunciation of "7 o'clock" is difficult to hear and suggests ways to practice pronunciation. The training unit evaluates the user's pronunciation and provides feedback on areas for improvement.

[0109] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0110] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, provision unit, and training unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects the user's voice using the microphone 38B of the smart device 14. The analysis unit analyzes the collected voice using the specific processing unit 290 of the data processing unit 12 and uses it to train the generation AI. The generation unit uses the specific processing unit 290 of the data processing unit 12 to perform reading aloud or transcription in the user's voice. The provision unit provides the generated voice or transcription to the user using the control unit 46A of the smart device 14. The training unit uses the specific processing unit 290 of the data processing unit 12 to perform training to improve articulation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, provision unit, and training unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects the user's voice using the microphone 238 of the smart glasses 214. The analysis unit analyzes the collected voice using the specific processing unit 290 of the data processing unit 12 and uses it to train the generation AI. The generation unit uses the specific processing unit 290 of the data processing unit 12 to perform reading aloud or transcription in the user's voice. The provision unit provides the generated voice or transcription to the user using the control unit 46A of the smart glasses 214. The training unit uses the specific processing unit 290 of the data processing unit 12 to perform training to improve articulation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, provision unit, and training unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects the user's voice using the microphone 238 of the headset terminal 314. The analysis unit analyzes the collected voice using the specific processing unit 290 of the data processing unit 12 and uses it to train the generation AI. The generation unit uses the specific processing unit 290 of the data processing unit 12 to perform reading aloud or transcription in the user's voice. The provision unit provides the generated voice and transcription to the user using the control unit 46A of the headset terminal 314. The training unit uses the specific processing unit 290 of the data processing unit 12 to perform training to improve articulation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] As shown in Figure 7, the 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.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0153] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, provision unit, and training unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit collects the user's voice using the microphone 238 of the robot 414. The analysis unit analyzes the collected voice using the specific processing unit 290 of the data processing unit 12 and uses it to train the generation AI. The generation unit uses the specific processing unit 290 of the data processing unit 12 to perform reading aloud or transcription in the user's voice. The provision unit provides the voice and transcription generated by the control unit 46A of the robot 414 to the user. The training unit uses the specific processing unit 290 of the data processing unit 12 to perform training to improve articulation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0162] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0164] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0165] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0166] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0170] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0171] 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.

[0172] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0173] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0174] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0175] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0177] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0178] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0179] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0180] (Note 1) A collection department that gathers user feedback, An analysis unit analyzes the voices collected by the aforementioned collection unit and uses this analysis to train a generation AI, Based on the data analyzed by the aforementioned analysis unit, the generation unit performs reading aloud or transcription in its own voice, A providing unit that provides the user with the audio and transcript generated by the generation unit, The system includes a training unit that performs speech improvement training based on the data generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of voice collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Analyze the user's past voice data and select the optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting voice data, the system filters out the user's current ambient noise to remove noise. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates the user's emotions and determines the priority of the voices to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting voice data, the system prioritizes collecting relevant audio by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting voice data, the system analyzes the user's social media activity and collects relevant audio. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During the analysis, the frequency characteristics of the voice are analyzed in detail to identify problems with articulation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, the system learns the user's pronunciation patterns and reflects their individual pronunciation characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the system references the user's past pronunciation data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, we refer to literature data related to the user's pronunciation to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is It estimates the user's emotions and adjusts the tone of the generated voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is During generation, the system generates audio that reflects the user's pronunciation characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is During generation, the system takes into account the user's pronunciation habits to create natural-sounding speech. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the speed of the generated audio based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is During generation, the system references the user's past pronunciation data to improve generation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is During generation, the system references literature data related to the user's pronunciation to improve generation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, It estimates the user's emotions and adjusts the format of the audio and transcript provided based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected by referring to the user's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the content to be delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned training department It estimates the user's emotions and adjusts the training content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned training department During training, the system selects the optimal training method by referring to the user's past pronunciation data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned training department During training, we create individualized training plans that take into account the user's pronunciation habits. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned training department It estimates the user's emotions and determines training priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned training department During training, the optimal training method is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned training department During training, the system analyzes the user's social media activity and suggests training methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection department that gathers user feedback, An analysis unit analyzes the voices collected by the aforementioned collection unit and uses them to train a generation AI, Based on the data analyzed by the aforementioned analysis unit, the generation unit performs reading aloud or transcription in its own voice, A providing unit that provides the user with the audio and transcript generated by the generation unit, The system includes a training unit that performs speech improvement training based on the data generated by the generation unit. A system characterized by the following features.

2. The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of voice collection based on the estimated emotions. The system according to feature 1.

3. The aforementioned collection unit is Analyze the user's past voice data and select the optimal collection method. The system according to feature 1.

4. The aforementioned collection unit is When collecting voice data, the system filters out the user's current ambient noise to remove noise. The system according to feature 1.

5. The aforementioned collection unit is It estimates the user's emotions and determines the priority of the voices to collect based on the estimated user emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting voice data, the system prioritizes collecting relevant audio by considering the user's geographical location. The system according to feature 1.

7. The aforementioned collection unit is When collecting voice data, the system analyzes the user's social media activity and collects relevant audio. The system according to feature 1.

8. The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system according to feature 1.

9. The aforementioned analysis unit, During the analysis, the frequency characteristics of the voice are analyzed in detail to identify problems with articulation. The system according to feature 1.

10. The aforementioned analysis unit, During analysis, the system learns the user's pronunciation patterns and reflects their individual pronunciation characteristics. The system according to feature 1.

Images