system

Abstract

The system according to this embodiment aims to provide users with audio that contains interrupted or noisy audio in a natural manner. [Solution] The system according to the embodiment comprises a collection unit, a speech recognition unit, a speech synthesis unit, and a provision unit. The collection unit collects speech. The speech recognition unit analyzes the speech collected by the collection unit and detects noise and interrupted portions. The speech synthesis unit generates natural speech based on the missing portions detected by the speech recognition unit. The provision unit provides the speech generated by the speech synthesis unit to the user.

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, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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 conventional technology, there is a problem that during a call in a place with poor radio waves, the voice may be interrupted or noise may be added, making it difficult to accurately understand the content of the speech.

[0005] The system according to the embodiment aims to complement voice including interrupted voice and noise in a natural form and provide it to the user.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a speech recognition unit, a speech synthesis unit, and a provision unit. The collection unit collects speech. The speech recognition unit analyzes the speech collected by the collection unit and detects noise and interruptions. The speech synthesis unit generates natural-sounding speech based on the missing parts detected by the speech recognition unit. The provision unit provides the speech generated by the speech synthesis unit to the user. [Effects of the Invention]

[0007] The system according to this embodiment can naturally complement and provide to the user audio that contains interrupted or noisy sounds. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple 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 �0, 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 voice enhancement system according to an embodiment of the present invention is a system for solving the problem of voice interruptions or noise during phone calls in areas with poor radio waves. This voice enhancement system can enhance voice in real time or later using a voice recognition model and a voice synthesis model that have been trained to handle noise. This makes it easier to understand what is being said and reduces the need to ask for clarification. Furthermore, this technology can also be applied to correct the speech of people who have difficulty with articulation. For example, when making a phone call in an area with poor radio waves, the voice may be interrupted or noise may be present. This is particularly relevant for people working in remote mountainous areas or underground, or for elderly people and others who have difficulty with articulation. In such situations, smooth communication becomes difficult. To solve this problem, a voice recognition model that has been trained to handle noise is used. The voice recognition model analyzes the voice during a call in real time and detects noise and interruptions. For example, if someone says "hello" during a call, due to radio wave interference, the voice may be transmitted as "hello...hello". In this case, the voice recognition model analyzes the voice "hello...hello" and identifies the missing part. Next, a speech synthesis model is used to fill in the missing parts. The speech synthesis model generates natural-sounding speech based on the missing parts identified by the speech recognition model. For example, if the speech is "Hello...", the speech synthesis model will generate the complete speech "Hello". This allows the person on the other end of the call to hear the completed speech instead of the interrupted speech. Furthermore, this technology can also be applied to correct the speech of people with speech difficulties. For example, when an elderly person says "Good morning", they may transmit the speech as "Good morning..." due to speech difficulties. In this case as well, the speech recognition model and speech synthesis model can be used to fill in the missing parts and generate natural-sounding speech. By applying this technology, it is possible to improve communication in areas with poor reception and to correct the speech of people with speech difficulties, enabling smoother communication. For example, people working in remote mountainous areas can communicate smoothly without interruptions during calls.Furthermore, elderly individuals can communicate with natural speech without interruptions due to speech difficulties. This means that the voice enhancement system can solve the problem of interrupted or noisy voices during calls in areas with poor reception, enabling smoother communication.

[0029] The voice enhancement system according to this embodiment comprises a collection unit, a voice recognition unit, a voice synthesis unit, and a provision unit. The collection unit collects voice. The collection unit can collect voice using, for example, a microphone. The collection unit can also collect voice using a device such as a smartphone or tablet. Furthermore, the collection unit may be equipped with a sensor for collecting ambient sound. For example, the collection unit can collect clear voice using a noise-canceling microphone. The collection unit can also collect voice using the built-in microphone of a smartphone. The collection unit can remove ambient noise using a sensor for collecting ambient sound. The voice recognition unit analyzes the voice collected by the collection unit and detects noise and interruptions. The voice recognition unit can analyze voice using, for example, a voice recognition algorithm. Furthermore, the voice recognition unit can analyze voice using a machine learning model. Furthermore, the voice recognition unit can analyze voice in real time. For example, the voice recognition unit can detect noise in voice using a voice recognition algorithm. The voice recognition unit can also detect interruptions in voice using a machine learning model. The speech recognition unit analyzes speech in real time and can instantly detect noise and interruptions. The speech synthesis unit generates natural-sounding speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. It can also generate speech using a speech database. Furthermore, it can generate speech using a machine learning model. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. The speech synthesis unit can also generate speech to fill in missing parts using a speech database. The speech synthesis unit can generate natural-sounding speech using a machine learning model. The delivery unit provides the speech generated by the speech synthesis unit to the user. The delivery unit can provide speech using, for example, a speaker. It can also provide speech using headphones. Furthermore, it can provide speech using devices such as smartphones and tablets.For example, the audio provider can provide the generated audio to the user in real time using a speaker. The audio provider can also provide the generated audio to the user using headphones. The audio provider can also provide the generated audio to the user using the speaker of a smartphone. As a result, the audio enhancement system according to this embodiment can compensate for audio interruptions and noise, enabling smooth communication.

[0030] The collection unit collects sound. The collection unit can collect sound using, for example, a microphone. Specifically, it can use a high-sensitivity microphone to clearly collect sound from long distances. The collection unit can also collect sound using devices such as smartphones and tablets. This allows for easy collection of sound data from devices carried by the user. Furthermore, the collection unit can be equipped with sensors for collecting ambient sound. For example, the collection unit can collect clear sound using a noise-canceling microphone. Noise-canceling technology effectively removes ambient noise, allowing for the collection of only the necessary sounds. The collection unit can also collect sound using the built-in microphone of a smartphone. This allows for the collection of sound from devices used daily without the need for special equipment. The collection unit can remove ambient noise using sensors for collecting ambient sound. For example, by arranging multiple microphones and identifying the direction of the sound source, it is possible to emphasize and collect only specific sounds. This allows the collection unit to collect high-quality sound data in diverse environments, improving the overall system performance. Furthermore, the collection unit has the function to transmit the collected audio data to the analysis unit in real time, enabling rapid processing and response.

[0031] The speech recognition unit analyzes the audio collected by the collection unit and detects noise and interruptions. For example, the speech recognition unit can analyze audio using a speech recognition algorithm. Specifically, the speech recognition algorithm extracts features from the audio signal and separates noise components to obtain clear audio data. The speech recognition unit can also analyze audio using a machine learning model. A machine learning model can learn from large amounts of audio data and detect noise and interruptions with high accuracy. Furthermore, the speech recognition unit can analyze audio in real time. For example, the speech recognition unit can detect noise in audio using a speech recognition algorithm. This removes unwanted noise from the collected audio data, resulting in clear audio. The speech recognition unit can also detect interruptions in audio using a machine learning model. A machine learning model learns patterns in audio data and can identify interruptions with high accuracy. The speech recognition unit can analyze audio in real time and immediately detect noise and interruptions. This allows the speech recognition unit to quickly and accurately analyze the collected audio data, improving the overall system performance. Furthermore, the speech recognition unit transmits the analysis results to the speech synthesis unit, enabling rapid completion of any missing parts.

[0032] The speech synthesis unit generates natural-sounding speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. Specifically, the speech synthesis algorithm analyzes the features of the speech data and can generate speech with natural intonation and rhythm. The speech synthesis unit can also generate speech using a speech database. The speech database contains a variety of speech samples, which can be used to generate speech to fill in the missing parts. Furthermore, the speech synthesis unit can generate speech using a machine learning model. A machine learning model can learn from a large amount of speech data and generate natural-sounding speech with high accuracy. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. This allows the speech used to fill in the missing parts to be seamlessly integrated with the original speech. The speech synthesis unit can also generate speech to fill in the missing parts using a speech database. The speech database contains a variety of speech samples, which can be used to generate speech to fill in the missing parts. The speech synthesis unit can generate natural-sounding speech using a machine learning model. This allows the speech synthesis unit to fill in the missing parts with high accuracy and improve the overall system performance. Furthermore, the speech synthesis unit transmits the generated speech to the delivery unit, preparing it for delivery to the user.

[0033] The delivery unit provides the user with the voice generated by the speech synthesis unit. The delivery unit can provide the voice using, for example, a speaker. Specifically, it can deliver clear and natural voice to the user using a high-quality speaker. The delivery unit can also provide the voice using headphones. This allows the user to hear the generated voice clearly, unaffected by the surrounding environment. Furthermore, the delivery unit can provide the voice using devices such as smartphones and tablets. This allows the user to easily listen to the generated voice from their portable device. For example, the delivery unit can provide the generated voice to the user in real time using a speaker. This allows the user to hear the generated voice immediately, facilitating smooth communication. The delivery unit can also provide the generated voice to the user using headphones. This allows the user to hear the generated voice clearly, unaffected by the surrounding environment. The delivery unit can provide the generated voice to the user using the speaker of a smartphone. This allows the user to easily listen to the generated voice from their portable device. Furthermore, the delivery unit can collect user feedback and continuously improve the quality and content of the voice it provides. This allows the delivery unit to provide high-quality voice to the user and improve the overall system performance.

[0034] The speech recognition unit can analyze the audio during a call in real time and detect noise and interruptions. The speech recognition unit analyzes the audio during a call in real time, for example, using a speech recognition algorithm. For example, the speech recognition unit can analyze the audio during a call in real time and detect noise. The speech recognition unit can also analyze the audio during a call in real time and detect interruptions. For example, the speech recognition unit can analyze the audio during a call in real time and instantly detect noise and interruptions. This allows for immediate completion by detecting interruptions and noise in the audio in real time. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without using AI. For example, the speech recognition unit can detect interruptions and noise in the audio during a call using an AI model that analyzes the audio during a call in real time and detects noise and interruptions.

[0035] The speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit. For example, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a speech synthesis algorithm. For example, the speech synthesis unit can generate speech with natural intonation based on the missing parts identified by the speech recognition unit. Furthermore, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a speech database. For example, the speech synthesis unit can generate speech to fill in the missing parts using a speech database. In addition, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a machine learning model. For example, the speech synthesis unit can generate natural speech using a machine learning model. This makes the content of the call clearer by filling in the missing parts with natural speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can generate natural speech using an AI model that generates natural speech based on the missing parts identified by the speech recognition unit.

[0036] The service provider can provide the generated audio to the user in real time. The service provider can provide the generated audio to the user in real time, for example, using a speaker. The service provider can also provide the generated audio to the user in real time using headphones. The service provider can also provide the generated audio to the user in real time using headphones. Furthermore, the service provider can provide the generated audio to the user in real time using devices such as smartphones and tablets. The service provider can provide the generated audio to the user in real time using the speaker of a smartphone. This enables smooth communication by providing audio that is supplemented in real time. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can provide audio using an AI model that provides generated audio to the user in real time.

[0037] The speech recognition unit can analyze the speech of a person with articulation difficulties and identify missing parts. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties using a speech recognition algorithm. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties and identify missing parts. Furthermore, the speech recognition unit can analyze the speech of a person with articulation difficulties using a machine learning model. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties using a machine learning model and identify missing parts. In addition, the speech recognition unit can analyze the speech of a person with articulation difficulties in real time and identify missing parts. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties in real time and identify missing parts. This allows for the clarification of the speech by supplementing the speech of a person with articulation difficulties. Some or all of the above-described processes in the speech recognition unit may be performed using AI, or not. For example, the speech recognition unit can identify missing parts using an AI model that analyzes the speech of a person with articulation difficulties and identifies missing parts.

[0038] The speech synthesis unit can generate natural speech to complement the speech of people with speech difficulties. For example, the speech synthesis unit can use a speech synthesis algorithm to generate natural speech to complement the speech of people with speech difficulties. For example, the speech synthesis unit can use a speech synthesis algorithm to generate speech with natural intonation to complement the speech of people with speech difficulties. Furthermore, the speech synthesis unit can use a speech database to generate natural speech to complement the speech of people with speech difficulties. In addition, the speech synthesis unit can use a machine learning model to generate natural speech to complement the speech of people with speech difficulties. This enables smooth communication by complementing the speech of people with speech difficulties with natural speech. Some or all of the above-described processes in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can generate natural-sounding speech using an AI model that generates natural-sounding speech to complement the speech of people who have difficulty with articulation.

[0039] The collection unit can analyze ambient noise and select the optimal collection method when collecting audio. For example, the collection unit can analyze ambient noise using an ambient noise analysis algorithm. For instance, it can collect ambient noise using a microphone and analyze it using an ambient noise analysis algorithm. The collection unit can also analyze ambient noise using noise cancellation technology. For example, it can collect ambient noise using a noise-canceling microphone and analyze it using a noise-canceling algorithm. Furthermore, the collection unit can analyze ambient noise in real time and select the optimal collection method. This improves the accuracy of audio collection by selecting the optimal collection method according to the ambient noise. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can improve the accuracy of audio collection by using an AI model that analyzes ambient noise and selects the optimal collection method.

[0040] The collection unit can learn the user's speech patterns during audio collection to improve collection accuracy. For example, the collection unit can learn the user's speech patterns using a machine learning algorithm. The collection unit can also learn the user's speech patterns using a dataset. Furthermore, the collection unit can learn the user's speech patterns using a dataset to improve audio collection accuracy. In addition, the collection unit can learn the user's speech patterns in real time to improve collection accuracy. This improves audio collection accuracy by learning the user's speech patterns. Some or all of the above processing in the collection unit may be performed using AI, or not. For example, the collection unit can improve audio collection accuracy by using an AI model that learns the user's speech patterns and improves collection accuracy.

[0041] The collection unit can prioritize the collection of highly relevant audio based on the user's geographical location information when collecting audio. For example, the collection unit can acquire the user's geographical location information using GPS data. For example, the collection unit can acquire the user's geographical location information using GPS data and prioritize the collection of highly relevant audio. The collection unit can also acquire the user's geographical location information using location information services. For example, the collection unit can acquire the user's geographical location information using location information services and prioritize the collection of highly relevant audio. Furthermore, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. For example, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. This improves collection accuracy by prioritizing the collection of highly relevant audio based on the user's geographical location information. Some or all of the above-described processes in the collection unit may be performed using AI, or not. For example, the collection unit can improve audio collection accuracy by using an AI model that prioritizes the collection of highly relevant audio based on the user's geographical location information.

[0042] The collection unit can analyze the user's social media activity and collect relevant audio when collecting audio. For example, the collection unit can analyze the user's social media activity using a social media analysis algorithm. For example, the collection unit can collect the user's social media posts and analyze them using a social media analysis algorithm. The collection unit can also analyze the frequency of the user's social media activity. For example, the collection unit can analyze the frequency of the user's social media activity and collect relevant audio. Furthermore, the collection unit can analyze the user's social media activity in real time and collect relevant audio. For example, the collection unit can analyze the user's social media activity in real time and collect relevant audio. This improves collection accuracy by collecting relevant audio based on the user's social media activity. 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 improve audio collection accuracy by using an AI model that analyzes the user's social media activity and collects relevant audio.

[0043] The speech recognition unit can optimize its recognition algorithm by referring to past audio data during speech recognition. For example, the speech recognition unit can store past audio data in a database and refer to it during speech recognition. Furthermore, the speech recognition unit can also refer to past audio data in real time. For example, the speech recognition unit can refer to past audio data in real time to optimize its recognition algorithm. In addition, the speech recognition unit can train a machine learning model using past audio data to optimize its recognition algorithm. This optimizes the recognition algorithm by referring to past audio data, thereby improving recognition accuracy. Some or all of the above-described processes in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can improve recognition accuracy by using an AI model that optimizes the recognition algorithm by referring to past audio data.

[0044] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit can classify the speech into categories and apply a recognition algorithm appropriate for each. For example, the speech recognition unit can apply different recognition algorithms depending on categories such as call audio, recorded audio, and live audio. The speech recognition unit can also enhance noise cancellation depending on the category of the speech. For example, in the case of call audio, the speech recognition unit can apply a recognition algorithm with enhanced noise cancellation. Furthermore, the speech recognition unit can apply recognition algorithms in real time depending on the category of the speech. For example, in the case of live audio, the speech recognition unit can apply an algorithm that can recognize in real time. This improves recognition accuracy by applying recognition algorithms according to the category of the speech. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can improve recognition accuracy by using an AI model that applies different recognition algorithms depending on the category of the speech.

[0045] The speech recognition unit can determine recognition priority based on the timing of speech submission during speech recognition. For example, the speech recognition unit can record the date and time of speech submission and refer to it during speech recognition to determine recognition priority. The speech recognition unit can also determine recognition priority in real time based on the timing of speech submission. For example, the speech recognition unit can determine recognition priority in real time based on the timing of speech submission. Furthermore, the speech recognition unit can train a machine learning model based on the timing of speech submission to determine recognition priority. For example, the speech recognition unit can train a machine learning model based on the timing of speech submission to determine recognition priority. This allows for priority recognition of the most recent speech by determining recognition priority based on the timing of speech submission. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can determine speech recognition priority using an AI model that determines recognition priority based on the timing of speech submission.

[0046] The speech recognition unit can adjust the recognition order based on the relevance of the speech during speech recognition. For example, the speech recognition unit can analyze the content of the speech and evaluate its relevance. For example, the speech recognition unit can analyze the content of the speech and prioritize the recognition of highly relevant speech. The speech recognition unit can also prioritize the recognition of speech containing specific keywords. For example, the speech recognition unit can prioritize the recognition of speech containing specific keywords and postpone the recognition of less relevant speech. Furthermore, the speech recognition unit can also prioritize the recognition of highly relevant speech based on the flow of the conversation. For example, the speech recognition unit can prioritize the recognition of highly relevant speech based on the flow of the conversation. In this way, important speech can be prioritized by adjusting the recognition order based on the relevance of the speech. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can adjust the order of speech recognition using an AI model that adjusts the recognition order based on the relevance of the speech.

[0047] The speech synthesis unit can adjust the level of detail of the synthesis based on the importance of the speech during speech synthesis. For example, the speech synthesis unit can analyze the content of the speech and evaluate its importance. For example, the speech synthesis unit can analyze the content of the speech and synthesize important speech in detail. The speech synthesis unit can also dynamically adjust the level of detail of the synthesis according to the importance of the speech. For example, the speech synthesis unit can dynamically adjust the level of detail of the synthesis according to the importance of the speech. Furthermore, the speech synthesis unit can train a machine learning model based on the importance of the speech and adjust the level of detail of the synthesis. For example, the speech synthesis unit can train a machine learning model based on the importance of the speech and adjust the level of detail of the synthesis. This allows important speech to be synthesized in more detail by adjusting the level of detail of the synthesis according to the importance of the speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the level of detail of speech synthesis using an AI model that adjusts the level of detail of the synthesis based on the importance of the speech.

[0048] The speech synthesis unit can apply different synthesis algorithms depending on the category of the speech during speech synthesis. For example, the speech synthesis unit can classify the categories of speech and apply a synthesis algorithm appropriate for each. For example, the speech synthesis unit can apply different synthesis algorithms depending on categories such as call speech, recorded speech, and live speech. The speech synthesis unit can also synthesize speech with a natural conversational tone depending on the category of speech. For example, in the case of call speech, the speech synthesis unit can synthesize speech with a natural conversational tone. Furthermore, the speech synthesis unit can apply synthesis algorithms in real time depending on the category of speech. For example, in the case of live speech, the speech synthesis unit can apply an algorithm that can be synthesized in real time. This makes it possible to perform more appropriate speech synthesis by applying synthesis algorithms according to the category of speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can improve the accuracy of speech synthesis by using an AI model that applies different synthesis algorithms depending on the category of speech.

[0049] The speech synthesis unit can determine the synthesis priority based on the audio submission date during speech synthesis. For example, the speech synthesis unit can record the audio submission date and time and refer to it during speech synthesis. For example, the speech synthesis unit can record the audio submission date and time and refer to it during speech synthesis to determine the synthesis priority. The speech synthesis unit can also determine the synthesis priority in real time based on the audio submission date. For example, the speech synthesis unit can determine the synthesis priority in real time based on the audio submission date. Furthermore, the speech synthesis unit can train a machine learning model based on the audio submission date to determine the synthesis priority. For example, the speech synthesis unit can train a machine learning model based on the audio submission date to determine the synthesis priority. This allows for the synthesis of the most recent audio first by determining the synthesis priority based on the audio submission date. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can determine the synthesis priority using an AI model that determines the synthesis priority based on the audio submission date.

[0050] The speech synthesis unit can adjust the synthesis order based on the relevance of the speech during synthesis. For example, the speech synthesis unit can analyze the content of the speech and evaluate its relevance. For example, the speech synthesis unit can analyze the content of the speech and prioritize the synthesis of highly relevant speech. The speech synthesis unit can also prioritize the synthesis of speech containing specific keywords. For example, the speech synthesis unit can prioritize the synthesis of speech containing specific keywords and postpone the synthesis of less relevant speech. Furthermore, the speech synthesis unit can also prioritize the synthesis of highly relevant speech based on the flow of the conversation. For example, the speech synthesis unit can prioritize the synthesis of highly relevant speech based on the flow of the conversation. This allows important speech to be synthesized preferentially by adjusting the synthesis order based on the relevance of the speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the synthesis order using an AI model that adjusts the synthesis order based on the relevance of the speech.

[0051] The service provider can select the optimal service delivery method by referring to the user's past operation history at the time of delivery. For example, the service provider can collect operation logs and analyze past operation history to select the optimal service delivery method. The service provider can also refer to the user's usage history. For example, the service provider can refer to the user's usage history to select the optimal service delivery method. Furthermore, the service provider can analyze the user's operation history in real time to select the optimal service delivery method. For example, the service provider can analyze the user's operation history in real time to select the optimal service delivery method. By selecting the optimal service delivery method based on the user's past operation history, the service provider can provide the user with the most suitable voice. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can select the voice delivery method using an AI model that selects the optimal service delivery method by referring to the user's past operation history.

[0052] The delivery unit can adjust the timing of delivery based on the user's current situation. For example, the delivery unit can monitor the user's activity status and evaluate the current situation. The delivery unit can also monitor the surrounding environment. For example, the delivery unit can monitor the surrounding environment and adjust the timing of delivery based on the current situation. Furthermore, the delivery unit can evaluate the user's situation in real time and adjust the timing of delivery. For example, the delivery unit can evaluate the user's situation in real time and adjust the timing of delivery. By adjusting the timing of delivery based on the user's current situation, audio can be delivered at a more appropriate time. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can adjust the timing of audio delivery using an AI model that adjusts the timing of delivery based on the user's current situation.

[0053] The delivery unit can select the optimal delivery method based on the user's device information at the time of delivery. For example, the delivery unit can identify the type of device and select a delivery method accordingly. For example, if the user is using a smartphone, the delivery unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the delivery unit can provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the delivery unit can provide a concise and highly visible display method. For example, the delivery unit can provide a display method optimized for the small screen of a smartwatch. By selecting the optimal delivery method based on the user's device information, the delivery unit can provide the user with the most suitable audio. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select an audio delivery method using an AI model that selects the optimal delivery method based on the user's device information.

[0054] The service provider can analyze the user's social media activity and provide relevant audio at the time of delivery. For example, the service provider can analyze the user's social media activity using a social media analysis algorithm. For example, the service provider can collect the user's social media posts and analyze them using a social media analysis algorithm. The service provider can also analyze the frequency of the user's social media activity. For example, the service provider can analyze the frequency of the user's social media activity and provide relevant audio. Furthermore, the service provider can analyze the user's social media activity in real time and provide relevant audio. For example, the service provider can analyze the user's social media activity in real time and provide relevant audio. This allows the service provider to provide the most relevant audio for the user based on their social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can improve the accuracy of audio delivery by using an AI model that analyzes the user's social media activity and provides relevant audio.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The sound collection unit can analyze ambient noise and select the optimal collection method when collecting audio. For example, the unit can analyze ambient noise using an ambient noise analysis algorithm. For instance, it can collect ambient noise using a microphone and analyze it using an ambient noise analysis algorithm. Furthermore, the unit can analyze ambient noise using noise cancellation technology. For example, it can collect ambient noise using a noise-canceling microphone and analyze it using a noise-canceling algorithm. In addition, the unit can analyze ambient noise in real time and select the optimal collection method. This improves the accuracy of audio collection by selecting the optimal collection method according to the ambient noise.

[0057] The audio collection unit can learn user speech patterns during audio collection to improve collection accuracy. For example, the collection unit can learn user speech patterns using machine learning algorithms. The collection unit can also learn user speech patterns using datasets. Furthermore, the collection unit can learn user speech patterns in real time to improve collection accuracy. This means that by learning user speech patterns, the accuracy of audio collection improves.

[0058] The collection unit can prioritize the collection of highly relevant audio based on the user's geographical location information during audio collection. For example, the collection unit can acquire the user's geographical location information using GPS data. Alternatively, the collection unit can acquire the user's geographical location information using GPS data and prioritize the collection of highly relevant audio. Furthermore, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. This improves collection accuracy by prioritizing the collection of highly relevant audio based on the user's geographical location information.

[0059] The data collection unit can analyze the user's social media activity and collect relevant audio when collecting audio. For example, the data collection unit can analyze the user's social media activity using a social media analysis algorithm. For instance, the data collection unit can collect the user's social media posts and analyze them using a social media analysis algorithm. The data collection unit can also analyze the frequency of the user's social media activity. Furthermore, the data collection unit can analyze the user's social media activity in real time and collect relevant audio. This improves collection accuracy by collecting relevant audio based on the user's social media activity.

[0060] The speech recognition unit can optimize its recognition algorithm by referring to past audio data during speech recognition. For example, the speech recognition unit can store past audio data in a database and refer to it during speech recognition. The speech recognition unit can also refer to past audio data in real time. Furthermore, the speech recognition unit can train a machine learning model using past audio data to optimize the recognition algorithm. As a result, the recognition algorithm is optimized by referring to past audio data, and recognition accuracy is improved.

[0061] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit can classify the speech into categories and apply a recognition algorithm appropriate for each. For instance, the speech recognition unit can apply different recognition algorithms depending on categories such as call audio, recorded audio, and live audio. The speech recognition unit can also enhance noise cancellation depending on the category of the speech. Furthermore, the speech recognition unit can apply recognition algorithms in real time depending on the category of the speech. This improves recognition accuracy by applying recognition algorithms according to the category of the speech.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The collection unit collects sound. The collection unit can collect sound using, for example, a microphone. It can also collect sound using a device such as a smartphone or tablet. Furthermore, the collection unit may be equipped with a sensor for collecting ambient sound. For example, the collection unit can collect clear sound using a noise-canceling microphone. The collection unit can also collect sound using the built-in microphone of a smartphone. The collection unit can remove ambient noise using a sensor for collecting ambient sound. Step 2: The speech recognition unit analyzes the audio collected by the collection unit and detects noise and interruptions. The speech recognition unit can analyze the audio using, for example, a speech recognition algorithm. It can also analyze the audio using a machine learning model. Furthermore, the speech recognition unit can analyze the audio in real time. For example, the speech recognition unit can detect noise in the audio using a speech recognition algorithm. The speech recognition unit can also detect interruptions in the audio using a machine learning model. The speech recognition unit can analyze the audio in real time and immediately detect noise and interruptions. Step 3: The speech synthesis unit generates natural speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. It can also generate speech using a speech database. Furthermore, the speech synthesis unit can generate speech using a machine learning model. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. The speech synthesis unit can also generate speech to fill in the missing parts using a speech database. The speech synthesis unit can generate natural speech using a machine learning model. Step 4: The delivery unit provides the user with the audio generated by the speech synthesis unit. The delivery unit can provide the audio using, for example, a speaker. It can also provide the audio using headphones. Furthermore, the delivery unit can provide the audio using devices such as smartphones and tablets. For example, the delivery unit can provide the generated audio to the user in real time using a speaker. The delivery unit can also provide the generated audio to the user using headphones. The delivery unit can provide the generated audio to the user using the speaker of a smartphone.

[0064] (Example of form 2) The voice enhancement system according to an embodiment of the present invention is a system for solving the problem of voice interruptions or noise during phone calls in areas with poor radio waves. This voice enhancement system can enhance voice in real time or later using a voice recognition model and a voice synthesis model that have been trained to handle noise. This makes it easier to understand what is being said and reduces the need to ask for clarification. Furthermore, this technology can also be applied to correct the speech of people who have difficulty with articulation. For example, when making a phone call in an area with poor radio waves, the voice may be interrupted or noise may be present. This is particularly relevant for people working in remote mountainous areas or underground, or for elderly people and others who have difficulty with articulation. In such situations, smooth communication becomes difficult. To solve this problem, a voice recognition model that has been trained to handle noise is used. The voice recognition model analyzes the voice during a call in real time and detects noise and interruptions. For example, if someone says "hello" during a call, due to radio wave interference, the voice may be transmitted as "hello...hello". In this case, the voice recognition model analyzes the voice "hello...hello" and identifies the missing part. Next, a speech synthesis model is used to fill in the missing parts. The speech synthesis model generates natural-sounding speech based on the missing parts identified by the speech recognition model. For example, if the speech is "Hello...", the speech synthesis model will generate the complete speech "Hello". This allows the person on the other end of the call to hear the completed speech instead of the interrupted speech. Furthermore, this technology can also be applied to correct the speech of people with speech difficulties. For example, when an elderly person says "Good morning", they may transmit the speech as "Good morning..." due to speech difficulties. In this case as well, the speech recognition model and speech synthesis model can be used to fill in the missing parts and generate natural-sounding speech. By applying this technology, it is possible to improve communication in areas with poor reception and to correct the speech of people with speech difficulties, enabling smoother communication. For example, people working in remote mountainous areas can communicate smoothly without interruptions during calls.Furthermore, elderly individuals can communicate with natural speech without interruptions due to speech difficulties. This means that the voice enhancement system can solve the problem of interrupted or noisy voices during calls in areas with poor reception, enabling smoother communication.

[0065] The voice enhancement system according to this embodiment comprises a collection unit, a voice recognition unit, a voice synthesis unit, and a provision unit. The collection unit collects voice. The collection unit can collect voice using, for example, a microphone. The collection unit can also collect voice using a device such as a smartphone or tablet. Furthermore, the collection unit may be equipped with a sensor for collecting ambient sound. For example, the collection unit can collect clear voice using a noise-canceling microphone. The collection unit can also collect voice using the built-in microphone of a smartphone. The collection unit can remove ambient noise using a sensor for collecting ambient sound. The voice recognition unit analyzes the voice collected by the collection unit and detects noise and interruptions. The voice recognition unit can analyze voice using, for example, a voice recognition algorithm. Furthermore, the voice recognition unit can analyze voice using a machine learning model. Furthermore, the voice recognition unit can analyze voice in real time. For example, the voice recognition unit can detect noise in voice using a voice recognition algorithm. The voice recognition unit can also detect interruptions in voice using a machine learning model. The speech recognition unit analyzes speech in real time and can instantly detect noise and interruptions. The speech synthesis unit generates natural-sounding speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. It can also generate speech using a speech database. Furthermore, it can generate speech using a machine learning model. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. The speech synthesis unit can also generate speech to fill in missing parts using a speech database. The speech synthesis unit can generate natural-sounding speech using a machine learning model. The delivery unit provides the speech generated by the speech synthesis unit to the user. The delivery unit can provide speech using, for example, a speaker. It can also provide speech using headphones. Furthermore, it can provide speech using devices such as smartphones and tablets.For example, the audio provider can provide the generated audio to the user in real time using a speaker. The audio provider can also provide the generated audio to the user using headphones. The audio provider can also provide the generated audio to the user using the speaker of a smartphone. As a result, the audio enhancement system according to this embodiment can compensate for audio interruptions and noise, enabling smooth communication.

[0066] The collection unit collects sound. The collection unit can collect sound using, for example, a microphone. Specifically, it can use a high-sensitivity microphone to clearly collect sound from long distances. The collection unit can also collect sound using devices such as smartphones and tablets. This allows for easy collection of sound data from devices carried by the user. Furthermore, the collection unit can be equipped with sensors for collecting ambient sound. For example, the collection unit can collect clear sound using a noise-canceling microphone. Noise-canceling technology effectively removes ambient noise, allowing for the collection of only the necessary sounds. The collection unit can also collect sound using the built-in microphone of a smartphone. This allows for the collection of sound from devices used daily without the need for special equipment. The collection unit can remove ambient noise using sensors for collecting ambient sound. For example, by arranging multiple microphones and identifying the direction of the sound source, it is possible to emphasize and collect only specific sounds. This allows the collection unit to collect high-quality sound data in diverse environments, improving the overall system performance. Furthermore, the collection unit has the function to transmit the collected audio data to the analysis unit in real time, enabling rapid processing and response.

[0067] The speech recognition unit analyzes the audio collected by the collection unit and detects noise and interruptions. For example, the speech recognition unit can analyze audio using a speech recognition algorithm. Specifically, the speech recognition algorithm extracts features from the audio signal and separates noise components to obtain clear audio data. The speech recognition unit can also analyze audio using a machine learning model. A machine learning model can learn from large amounts of audio data and detect noise and interruptions with high accuracy. Furthermore, the speech recognition unit can analyze audio in real time. For example, the speech recognition unit can detect noise in audio using a speech recognition algorithm. This removes unwanted noise from the collected audio data, resulting in clear audio. The speech recognition unit can also detect interruptions in audio using a machine learning model. A machine learning model learns patterns in audio data and can identify interruptions with high accuracy. The speech recognition unit can analyze audio in real time and immediately detect noise and interruptions. This allows the speech recognition unit to quickly and accurately analyze the collected audio data, improving the overall system performance. Furthermore, the speech recognition unit transmits the analysis results to the speech synthesis unit, enabling rapid completion of any missing parts.

[0068] The speech synthesis unit generates natural-sounding speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. Specifically, the speech synthesis algorithm analyzes the features of the speech data and can generate speech with natural intonation and rhythm. The speech synthesis unit can also generate speech using a speech database. The speech database contains a variety of speech samples, which can be used to generate speech to fill in the missing parts. Furthermore, the speech synthesis unit can generate speech using a machine learning model. A machine learning model can learn from a large amount of speech data and generate natural-sounding speech with high accuracy. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. This allows the speech used to fill in the missing parts to be seamlessly integrated with the original speech. The speech synthesis unit can also generate speech to fill in the missing parts using a speech database. The speech database contains a variety of speech samples, which can be used to generate speech to fill in the missing parts. The speech synthesis unit can generate natural-sounding speech using a machine learning model. This allows the speech synthesis unit to fill in the missing parts with high accuracy and improve the overall system performance. Furthermore, the speech synthesis unit transmits the generated speech to the delivery unit, preparing it for delivery to the user.

[0069] The delivery unit provides the user with the voice generated by the speech synthesis unit. The delivery unit can provide the voice using, for example, a speaker. Specifically, it can deliver clear and natural voice to the user using a high-quality speaker. The delivery unit can also provide the voice using headphones. This allows the user to hear the generated voice clearly, unaffected by the surrounding environment. Furthermore, the delivery unit can provide the voice using devices such as smartphones and tablets. This allows the user to easily listen to the generated voice from their portable device. For example, the delivery unit can provide the generated voice to the user in real time using a speaker. This allows the user to hear the generated voice immediately, facilitating smooth communication. The delivery unit can also provide the generated voice to the user using headphones. This allows the user to hear the generated voice clearly, unaffected by the surrounding environment. The delivery unit can provide the generated voice to the user using the speaker of a smartphone. This allows the user to easily listen to the generated voice from their portable device. Furthermore, the delivery unit can collect user feedback and continuously improve the quality and content of the voice it provides. This allows the delivery unit to provide high-quality voice to the user and improve the overall system performance.

[0070] The speech recognition unit can analyze the audio during a call in real time and detect noise and interruptions. The speech recognition unit analyzes the audio during a call in real time, for example, using a speech recognition algorithm. For example, the speech recognition unit can analyze the audio during a call in real time and detect noise. The speech recognition unit can also analyze the audio during a call in real time and detect interruptions. For example, the speech recognition unit can analyze the audio during a call in real time and instantly detect noise and interruptions. This allows for immediate completion by detecting interruptions and noise in the audio in real time. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without using AI. For example, the speech recognition unit can detect interruptions and noise in the audio during a call using an AI model that analyzes the audio during a call in real time and detects noise and interruptions.

[0071] The speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit. For example, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a speech synthesis algorithm. For example, the speech synthesis unit can generate speech with natural intonation based on the missing parts identified by the speech recognition unit. Furthermore, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a speech database. For example, the speech synthesis unit can generate speech to fill in the missing parts using a speech database. In addition, the speech synthesis unit can generate natural speech based on the missing parts identified by the speech recognition unit using a machine learning model. For example, the speech synthesis unit can generate natural speech using a machine learning model. This makes the content of the call clearer by filling in the missing parts with natural speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can generate natural speech using an AI model that generates natural speech based on the missing parts identified by the speech recognition unit.

[0072] The service provider can provide the generated audio to the user in real time. The service provider can provide the generated audio to the user in real time, for example, using a speaker. The service provider can also provide the generated audio to the user in real time using headphones. The service provider can also provide the generated audio to the user in real time using headphones. Furthermore, the service provider can provide the generated audio to the user in real time using devices such as smartphones and tablets. The service provider can provide the generated audio to the user in real time using the speaker of a smartphone. This enables smooth communication by providing audio that is supplemented in real time. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can provide audio using an AI model that provides generated audio to the user in real time.

[0073] The speech recognition unit can analyze the speech of a person with articulation difficulties and identify missing parts. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties using a speech recognition algorithm. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties and identify missing parts. Furthermore, the speech recognition unit can analyze the speech of a person with articulation difficulties using a machine learning model. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties using a machine learning model and identify missing parts. In addition, the speech recognition unit can analyze the speech of a person with articulation difficulties in real time and identify missing parts. For example, the speech recognition unit can analyze the speech of a person with articulation difficulties in real time and identify missing parts. This allows for the clarification of the speech by supplementing the speech of a person with articulation difficulties. Some or all of the above-described processes in the speech recognition unit may be performed using AI, or not. For example, the speech recognition unit can identify missing parts using an AI model that analyzes the speech of a person with articulation difficulties and identifies missing parts.

[0074] The speech synthesis unit can generate natural speech to complement the speech of people with speech difficulties. For example, the speech synthesis unit can use a speech synthesis algorithm to generate natural speech to complement the speech of people with speech difficulties. For example, the speech synthesis unit can use a speech synthesis algorithm to generate speech with natural intonation to complement the speech of people with speech difficulties. Furthermore, the speech synthesis unit can use a speech database to generate natural speech to complement the speech of people with speech difficulties. In addition, the speech synthesis unit can use a machine learning model to generate natural speech to complement the speech of people with speech difficulties. This enables smooth communication by complementing the speech of people with speech difficulties with natural speech. Some or all of the above-described processes in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can generate natural-sounding speech using an AI model that generates natural-sounding speech to complement the speech of people who have difficulty with articulation.

[0075] The data collection unit can estimate the user's emotions and adjust the timing of audio collection based on the estimated emotions. For example, the data collection unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate their emotions using a facial recognition algorithm. The data collection unit can also estimate the user's emotions using speech analysis technology. For example, it can collect the user's voice using a microphone and estimate their emotions using a speech analysis algorithm. Furthermore, the data collection unit can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for more appropriate audio collection by adjusting the timing of audio collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can adjust the timing of audio collection using an AI model that estimates the user's emotions and adjusts the timing of audio collection based on the estimated user emotions.

[0076] The collection unit can analyze ambient noise and select the optimal collection method when collecting audio. For example, the collection unit can analyze ambient noise using an ambient noise analysis algorithm. For instance, it can collect ambient noise using a microphone and analyze it using an ambient noise analysis algorithm. The collection unit can also analyze ambient noise using noise cancellation technology. For example, it can collect ambient noise using a noise-canceling microphone and analyze it using a noise-canceling algorithm. Furthermore, the collection unit can analyze ambient noise in real time and select the optimal collection method. This improves the accuracy of audio collection by selecting the optimal collection method according to the ambient noise. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can improve the accuracy of audio collection by using an AI model that analyzes ambient noise and selects the optimal collection method.

[0077] The collection unit can learn the user's speech patterns during audio collection to improve collection accuracy. For example, the collection unit can learn the user's speech patterns using a machine learning algorithm. The collection unit can also learn the user's speech patterns using a dataset. Furthermore, the collection unit can learn the user's speech patterns using a dataset to improve audio collection accuracy. In addition, the collection unit can learn the user's speech patterns in real time to improve collection accuracy. This improves audio collection accuracy by learning the user's speech patterns. Some or all of the above processing in the collection unit may be performed using AI, or not. For example, the collection unit can improve audio collection accuracy by using an AI model that learns the user's speech patterns and improves collection accuracy.

[0078] The data collection unit can estimate the user's emotions and determine the priority of the audio to be collected based on the estimated emotions. For example, the data collection unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. Alternatively, the data collection unit can estimate the user's emotions using voice analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a voice analysis algorithm. Furthermore, the data collection unit can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for the priority of audio collection based on the user's emotions, prioritizing important audio. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can determine the priority of audio by using an AI model that estimates the user's emotions and determines the priority of audio to be collected based on the estimated user emotions.

[0079] The collection unit can prioritize the collection of highly relevant audio based on the user's geographical location information when collecting audio. For example, the collection unit can acquire the user's geographical location information using GPS data. For example, the collection unit can acquire the user's geographical location information using GPS data and prioritize the collection of highly relevant audio. The collection unit can also acquire the user's geographical location information using location information services. For example, the collection unit can acquire the user's geographical location information using location information services and prioritize the collection of highly relevant audio. Furthermore, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. For example, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. This improves collection accuracy by prioritizing the collection of highly relevant audio based on the user's geographical location information. Some or all of the above-described processes in the collection unit may be performed using AI, or not. For example, the collection unit can improve audio collection accuracy by using an AI model that prioritizes the collection of highly relevant audio based on the user's geographical location information.

[0080] The collection unit can analyze the user's social media activity and collect relevant audio when collecting audio. For example, the collection unit can analyze the user's social media activity using a social media analysis algorithm. For example, the collection unit can collect the user's social media posts and analyze them using a social media analysis algorithm. The collection unit can also analyze the frequency of the user's social media activity. For example, the collection unit can analyze the frequency of the user's social media activity and collect relevant audio. Furthermore, the collection unit can analyze the user's social media activity in real time and collect relevant audio. For example, the collection unit can analyze the user's social media activity in real time and collect relevant audio. This improves collection accuracy by collecting relevant audio based on the user's social media activity. 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 improve audio collection accuracy by using an AI model that analyzes the user's social media activity and collects relevant audio.

[0081] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated emotions. For example, the speech recognition unit can estimate the user's emotions using facial expression recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial expression recognition algorithm. The speech recognition unit can also estimate the user's emotions using speech analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a speech analysis algorithm. Furthermore, the speech recognition unit can also estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for improved recognition accuracy by adjusting the accuracy of speech recognition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can adjust the accuracy of speech recognition using an AI model that estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated user emotions.

[0082] The speech recognition unit can optimize its recognition algorithm by referring to past audio data during speech recognition. For example, the speech recognition unit can store past audio data in a database and refer to it during speech recognition. Furthermore, the speech recognition unit can also refer to past audio data in real time. For example, the speech recognition unit can refer to past audio data in real time to optimize its recognition algorithm. In addition, the speech recognition unit can train a machine learning model using past audio data to optimize its recognition algorithm. This optimizes the recognition algorithm by referring to past audio data, thereby improving recognition accuracy. Some or all of the above-described processes in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can improve recognition accuracy by using an AI model that optimizes the recognition algorithm by referring to past audio data.

[0083] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit can classify the speech into categories and apply a recognition algorithm appropriate for each. For example, the speech recognition unit can apply different recognition algorithms depending on categories such as call audio, recorded audio, and live audio. The speech recognition unit can also enhance noise cancellation depending on the category of the speech. For example, in the case of call audio, the speech recognition unit can apply a recognition algorithm with enhanced noise cancellation. Furthermore, the speech recognition unit can apply recognition algorithms in real time depending on the category of the speech. For example, in the case of live audio, the speech recognition unit can apply an algorithm that can recognize in real time. This improves recognition accuracy by applying recognition algorithms according to the category of the speech. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can improve recognition accuracy by using an AI model that applies different recognition algorithms depending on the category of the speech.

[0084] The speech recognition unit can estimate the user's emotions and determine the priority of speech recognition based on the estimated emotions. For example, the speech recognition unit can estimate the user's emotions using facial expression recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial expression recognition algorithm. The speech recognition unit can also estimate the user's emotions using speech analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a speech analysis algorithm. Furthermore, the speech recognition unit can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for the priority of speech recognition based on the user's emotions, enabling the recognition of important speech. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can determine the priority of speech recognition using an AI model that estimates the user's emotions and determines the priority of speech recognition based on the estimated user emotions.

[0085] The speech recognition unit can determine recognition priority based on the timing of speech submission during speech recognition. For example, the speech recognition unit can record the date and time of speech submission and refer to it during speech recognition to determine recognition priority. The speech recognition unit can also determine recognition priority in real time based on the timing of speech submission. For example, the speech recognition unit can determine recognition priority in real time based on the timing of speech submission. Furthermore, the speech recognition unit can train a machine learning model based on the timing of speech submission to determine recognition priority. For example, the speech recognition unit can train a machine learning model based on the timing of speech submission to determine recognition priority. This allows for priority recognition of the most recent speech by determining recognition priority based on the timing of speech submission. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can determine speech recognition priority using an AI model that determines recognition priority based on the timing of speech submission.

[0086] The speech recognition unit can adjust the recognition order based on the relevance of the speech during speech recognition. For example, the speech recognition unit can analyze the content of the speech and evaluate its relevance. For example, the speech recognition unit can analyze the content of the speech and prioritize the recognition of highly relevant speech. The speech recognition unit can also prioritize the recognition of speech containing specific keywords. For example, the speech recognition unit can prioritize the recognition of speech containing specific keywords and postpone the recognition of less relevant speech. Furthermore, the speech recognition unit can also prioritize the recognition of highly relevant speech based on the flow of the conversation. For example, the speech recognition unit can prioritize the recognition of highly relevant speech based on the flow of the conversation. In this way, important speech can be prioritized by adjusting the recognition order based on the relevance of the speech. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can adjust the order of speech recognition using an AI model that adjusts the recognition order based on the relevance of the speech.

[0087] The speech synthesis unit can estimate the user's emotions and adjust the speech synthesis expression method based on the estimated user emotions. For example, the speech synthesis unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. Alternatively, the speech synthesis unit can estimate the user's emotions using speech analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a speech analysis algorithm. Furthermore, the speech synthesis unit can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for more natural-sounding speech by adjusting the speech synthesis expression method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the speech synthesis expression method using an AI model that estimates the user's emotions and adjusts the speech synthesis expression method based on the estimated user emotions.

[0088] The speech synthesis unit can adjust the level of detail of the synthesis based on the importance of the speech during speech synthesis. For example, the speech synthesis unit can analyze the content of the speech and evaluate its importance. For example, the speech synthesis unit can analyze the content of the speech and synthesize important speech in detail. The speech synthesis unit can also dynamically adjust the level of detail of the synthesis according to the importance of the speech. For example, the speech synthesis unit can dynamically adjust the level of detail of the synthesis according to the importance of the speech. Furthermore, the speech synthesis unit can train a machine learning model based on the importance of the speech and adjust the level of detail of the synthesis. For example, the speech synthesis unit can train a machine learning model based on the importance of the speech and adjust the level of detail of the synthesis. This allows important speech to be synthesized in more detail by adjusting the level of detail of the synthesis according to the importance of the speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the level of detail of speech synthesis using an AI model that adjusts the level of detail of the synthesis based on the importance of the speech.

[0089] The speech synthesis unit can apply different synthesis algorithms depending on the category of the speech during speech synthesis. For example, the speech synthesis unit can classify the categories of speech and apply a synthesis algorithm appropriate for each. For example, the speech synthesis unit can apply different synthesis algorithms depending on categories such as call speech, recorded speech, and live speech. The speech synthesis unit can also synthesize speech with a natural conversational tone depending on the category of speech. For example, in the case of call speech, the speech synthesis unit can synthesize speech with a natural conversational tone. Furthermore, the speech synthesis unit can apply synthesis algorithms in real time depending on the category of speech. For example, in the case of live speech, the speech synthesis unit can apply an algorithm that can be synthesized in real time. This makes it possible to perform more appropriate speech synthesis by applying synthesis algorithms according to the category of speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can improve the accuracy of speech synthesis by using an AI model that applies different synthesis algorithms depending on the category of speech.

[0090] The speech synthesis unit can estimate the user's emotions and adjust the length of the synthesized speech based on the estimated emotions. For example, the speech synthesis unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. Alternatively, the speech synthesis unit can estimate the user's emotions using speech analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a speech analysis algorithm. Furthermore, the speech synthesis unit can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for the provision of more appropriate speech by adjusting the length of the synthesized speech according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the length of the speech synthesis using an AI model that estimates the user's emotions and adjusts the length of the speech synthesis based on the estimated user emotions.

[0091] The speech synthesis unit can determine the synthesis priority based on the audio submission date during speech synthesis. For example, the speech synthesis unit can record the audio submission date and time and refer to it during speech synthesis. For example, the speech synthesis unit can record the audio submission date and time and refer to it during speech synthesis to determine the synthesis priority. The speech synthesis unit can also determine the synthesis priority in real time based on the audio submission date. For example, the speech synthesis unit can determine the synthesis priority in real time based on the audio submission date. Furthermore, the speech synthesis unit can train a machine learning model based on the audio submission date to determine the synthesis priority. For example, the speech synthesis unit can train a machine learning model based on the audio submission date to determine the synthesis priority. This allows for the synthesis of the most recent audio first by determining the synthesis priority based on the audio submission date. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can determine the synthesis priority using an AI model that determines the synthesis priority based on the audio submission date.

[0092] The speech synthesis unit can adjust the synthesis order based on the relevance of the speech during synthesis. For example, the speech synthesis unit can analyze the content of the speech and evaluate its relevance. For example, the speech synthesis unit can analyze the content of the speech and prioritize the synthesis of highly relevant speech. The speech synthesis unit can also prioritize the synthesis of speech containing specific keywords. For example, the speech synthesis unit can prioritize the synthesis of speech containing specific keywords and postpone the synthesis of less relevant speech. Furthermore, the speech synthesis unit can also prioritize the synthesis of highly relevant speech based on the flow of the conversation. For example, the speech synthesis unit can prioritize the synthesis of highly relevant speech based on the flow of the conversation. This allows important speech to be synthesized preferentially by adjusting the synthesis order based on the relevance of the speech. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can adjust the synthesis order using an AI model that adjusts the synthesis order based on the relevance of the speech.

[0093] The service provider can estimate the user's emotions and adjust the way it delivers the audio based on the estimated emotions. For example, the service provider can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the emotions using a facial recognition algorithm. Alternatively, the service provider can estimate the user's emotions using voice analysis technology. For example, it can collect the user's voice using a microphone and estimate the emotions using a voice analysis algorithm. Furthermore, the service provider can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the emotions using a biometric algorithm. This allows the service provider to deliver more appropriate audio by adjusting the way it delivers the audio according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can adjust the way the voice is expressed using an AI model that estimates the user's emotions and adjusts the way the voice is expressed based on the estimated user emotions.

[0094] The service provider can select the optimal service delivery method by referring to the user's past operation history at the time of delivery. For example, the service provider can collect operation logs and analyze past operation history to select the optimal service delivery method. The service provider can also refer to the user's usage history. For example, the service provider can refer to the user's usage history to select the optimal service delivery method. Furthermore, the service provider can analyze the user's operation history in real time to select the optimal service delivery method. For example, the service provider can analyze the user's operation history in real time to select the optimal service delivery method. By selecting the optimal service delivery method based on the user's past operation history, the service provider can provide the user with the most suitable voice. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can select the voice delivery method using an AI model that selects the optimal service delivery method by referring to the user's past operation history.

[0095] The delivery unit can adjust the timing of delivery based on the user's current situation. For example, the delivery unit can monitor the user's activity status and evaluate the current situation. The delivery unit can also monitor the surrounding environment. For example, the delivery unit can monitor the surrounding environment and adjust the timing of delivery based on the current situation. Furthermore, the delivery unit can evaluate the user's situation in real time and adjust the timing of delivery. For example, the delivery unit can evaluate the user's situation in real time and adjust the timing of delivery. By adjusting the timing of delivery based on the user's current situation, audio can be delivered at a more appropriate time. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can adjust the timing of audio delivery using an AI model that adjusts the timing of delivery based on the user's current situation.

[0096] The service provider can estimate the user's emotions and determine the priority of the audio to be provided based on the estimated emotions. For example, the service provider can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. Alternatively, the service provider can estimate the user's emotions using voice analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a voice analysis algorithm. Furthermore, the service provider can estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows the service provider to prioritize the audio provided according to the user's emotions, thereby prioritizing the delivery of important audio. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can determine the priority of voices by using an AI model that estimates the user's emotions and determines the priority of voices to be provided based on the estimated user emotions.

[0097] The delivery unit can select the optimal delivery method based on the user's device information at the time of delivery. For example, the delivery unit can identify the type of device and select a delivery method accordingly. For example, if the user is using a smartphone, the delivery unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the delivery unit can provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the delivery unit can provide a concise and highly visible display method. For example, the delivery unit can provide a display method optimized for the small screen of a smartwatch. By selecting the optimal delivery method based on the user's device information, the delivery unit can provide the user with the most suitable audio. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select an audio delivery method using an AI model that selects the optimal delivery method based on the user's device information.

[0098] The service provider can analyze the user's social media activity and provide relevant audio at the time of delivery. For example, the service provider can analyze the user's social media activity using a social media analysis algorithm. For example, the service provider can collect the user's social media posts and analyze them using a social media analysis algorithm. The service provider can also analyze the frequency of the user's social media activity. For example, the service provider can analyze the frequency of the user's social media activity and provide relevant audio. Furthermore, the service provider can analyze the user's social media activity in real time and provide relevant audio. For example, the service provider can analyze the user's social media activity in real time and provide relevant audio. This allows the service provider to provide the most relevant audio for the user based on their social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can improve the accuracy of audio delivery by using an AI model that analyzes the user's social media activity and provides relevant audio.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The data collection unit can estimate the user's emotions and adjust the timing of audio collection based on the estimated emotions. For example, the data collection unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. The data collection unit can also estimate the user's emotions using voice analysis technology. For example, it can collect the user's voice using a microphone and estimate the user's emotions using a voice analysis algorithm. Furthermore, the data collection unit can also estimate the user's emotions using biometric technology. For example, it can measure heart rate and skin electrical activity and estimate the user's emotions using a biometric algorithm. This allows for more appropriate audio collection by adjusting the timing of audio collection according to the user's emotions.

[0101] The sound collection unit can analyze ambient noise and select the optimal collection method when collecting audio. For example, the unit can analyze ambient noise using an ambient noise analysis algorithm. For instance, it can collect ambient noise using a microphone and analyze it using an ambient noise analysis algorithm. Furthermore, the unit can analyze ambient noise using noise cancellation technology. For example, it can collect ambient noise using a noise-canceling microphone and analyze it using a noise-canceling algorithm. In addition, the unit can analyze ambient noise in real time and select the optimal collection method. This improves the accuracy of audio collection by selecting the optimal collection method according to the ambient noise.

[0102] The audio collection unit can learn user speech patterns during audio collection to improve collection accuracy. For example, the collection unit can learn user speech patterns using machine learning algorithms. The collection unit can also learn user speech patterns using datasets. Furthermore, the collection unit can learn user speech patterns in real time to improve collection accuracy. This means that by learning user speech patterns, the accuracy of audio collection improves.

[0103] The data collection unit can estimate the user's emotions and determine the priority of the audio to be collected based on the estimated emotions. For example, the data collection unit can estimate the user's emotions using facial recognition technology. For instance, the data collection unit can capture the user's facial expressions using a camera and estimate the user's emotions using a facial recognition algorithm. The data collection unit can also estimate the user's emotions using audio analysis technology. Furthermore, the data collection unit can estimate the user's emotions using biometric technology. This allows for the priority of audio to be determined according to the user's emotions, thereby prioritizing the collection of important audio.

[0104] The collection unit can prioritize the collection of highly relevant audio based on the user's geographical location information during audio collection. For example, the collection unit can acquire the user's geographical location information using GPS data. Alternatively, the collection unit can acquire the user's geographical location information using GPS data and prioritize the collection of highly relevant audio. Furthermore, the collection unit can acquire the user's geographical location information in real time and prioritize the collection of highly relevant audio. This improves collection accuracy by prioritizing the collection of highly relevant audio based on the user's geographical location information.

[0105] The data collection unit can analyze the user's social media activity and collect relevant audio when collecting audio. For example, the data collection unit can analyze the user's social media activity using a social media analysis algorithm. For instance, the data collection unit can collect the user's social media posts and analyze them using a social media analysis algorithm. The data collection unit can also analyze the frequency of the user's social media activity. Furthermore, the data collection unit can analyze the user's social media activity in real time and collect relevant audio. This improves collection accuracy by collecting relevant audio based on the user's social media activity.

[0106] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated emotions. For example, the speech recognition unit can estimate the user's emotions using facial expression recognition technology. For instance, the speech recognition unit can capture the user's facial expressions using a camera and estimate the user's emotions using a facial expression recognition algorithm. The speech recognition unit can also estimate the user's emotions using speech analysis technology. Furthermore, the speech recognition unit can estimate the user's emotions using biometric technology. By adjusting the accuracy of speech recognition according to the user's emotions, the recognition accuracy can be improved.

[0107] The speech recognition unit can optimize its recognition algorithm by referring to past audio data during speech recognition. For example, the speech recognition unit can store past audio data in a database and refer to it during speech recognition. The speech recognition unit can also refer to past audio data in real time. Furthermore, the speech recognition unit can train a machine learning model using past audio data to optimize the recognition algorithm. As a result, the recognition algorithm is optimized by referring to past audio data, and recognition accuracy is improved.

[0108] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit can classify the speech into categories and apply a recognition algorithm appropriate for each. For instance, the speech recognition unit can apply different recognition algorithms depending on categories such as call audio, recorded audio, and live audio. The speech recognition unit can also enhance noise cancellation depending on the category of the speech. Furthermore, the speech recognition unit can apply recognition algorithms in real time depending on the category of the speech. This improves recognition accuracy by applying recognition algorithms according to the category of the speech.

[0109] The speech recognition unit can estimate the user's emotions and determine the priority of speech recognition based on the estimated emotions. For example, the speech recognition unit can estimate the user's emotions using facial expression recognition technology. For instance, the speech recognition unit can capture the user's facial expressions using a camera and estimate the user's emotions using a facial expression recognition algorithm. The speech recognition unit can also estimate the user's emotions using speech analysis technology. Furthermore, the speech recognition unit can estimate the user's emotions using biometric technology. By determining the priority of speech recognition according to the user's emotions, important speech can be recognized preferentially.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The collection unit collects sound. The collection unit can collect sound using, for example, a microphone. It can also collect sound using a device such as a smartphone or tablet. Furthermore, the collection unit may be equipped with a sensor for collecting ambient sound. For example, the collection unit can collect clear sound using a noise-canceling microphone. The collection unit can also collect sound using the built-in microphone of a smartphone. The collection unit can remove ambient noise using a sensor for collecting ambient sound. Step 2: The speech recognition unit analyzes the audio collected by the collection unit and detects noise and interruptions. The speech recognition unit can analyze the audio using, for example, a speech recognition algorithm. It can also analyze the audio using a machine learning model. Furthermore, the speech recognition unit can analyze the audio in real time. For example, the speech recognition unit can detect noise in the audio using a speech recognition algorithm. The speech recognition unit can also detect interruptions in the audio using a machine learning model. The speech recognition unit can analyze the audio in real time and immediately detect noise and interruptions. Step 3: The speech synthesis unit generates natural speech based on the missing parts detected by the speech recognition unit. The speech synthesis unit can generate speech using, for example, a speech synthesis algorithm. It can also generate speech using a speech database. Furthermore, the speech synthesis unit can generate speech using a machine learning model. For example, the speech synthesis unit can generate speech with natural intonation using a speech synthesis algorithm. The speech synthesis unit can also generate speech to fill in the missing parts using a speech database. The speech synthesis unit can generate natural speech using a machine learning model. Step 4: The delivery unit provides the user with the audio generated by the speech synthesis unit. The delivery unit can provide the audio using, for example, a speaker. It can also provide the audio using headphones. Furthermore, the delivery unit can provide the audio using devices such as smartphones and tablets. For example, the delivery unit can provide the generated audio to the user in real time using a speaker. The delivery unit can also provide the generated audio to the user using headphones. The delivery unit can provide the generated audio to the user using the speaker of a smartphone.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements described above, including the collection unit, speech recognition unit, speech synthesis unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit can collect speech using the microphone and sensors of the smart device 14. The speech recognition unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech and detects noise and interruptions. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12, which generates natural speech based on the detected missing parts. The provision unit provides the generated speech to the user using the speaker or headphones of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements described above, including the collection unit, speech recognition unit, speech synthesis unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit can collect speech using the microphone and sensors of the smart glasses 214. The speech recognition unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected speech and detects noise and interruptions. The speech synthesis unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates natural speech based on the detected missing parts. The provision unit provides the generated speech to the user using the speaker or headphones of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the collection unit, speech recognition unit, speech synthesis unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit can collect speech using the microphone and sensors of the headset terminal 314. The speech recognition unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech and detects noise and interruptions. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12, which generates natural speech based on the detected missing parts. The provision unit provides the generated speech to the user using the speaker or headphones of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the collection unit, speech recognition unit, speech synthesis unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit can collect speech using the microphone or sensors of the robot 414. The speech recognition unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech and detects noise and interruptions. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12, which generates natural speech based on the detected missing parts. The provision unit provides the generated speech to the user using the speaker or headphones of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) A collection unit that collects sound, A speech recognition unit analyzes the audio collected by the aforementioned collection unit and detects noise and interruptions, A speech synthesis unit generates natural speech based on the missing portion detected by the speech recognition unit, The system includes a providing unit that provides the voice generated by the voice synthesis unit to the user. A system characterized by the following features. (Note 2) The aforementioned speech recognition unit, It analyzes the audio during a call in real time to detect noise and interruptions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned speech synthesis unit, The speech recognition unit generates natural-sounding speech based on the missing parts it identifies. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Provides the generated audio to the user in real time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned speech recognition unit, Analyze the speech of people with speech difficulties to identify missing parts. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech synthesis unit, Generates natural-sounding speech to complement the speech of people with speech difficulties. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of audio collection based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When collecting audio, the system analyzes ambient noise and selects the optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is During voice collection, the system learns the user's speech patterns to improve collection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and determines the priority of audio to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting audio, the system prioritizes collecting audio that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting audio, 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 13) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned speech recognition unit, During speech recognition, the recognition algorithm is optimized by referring to past speech data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned speech recognition unit, During speech recognition, different recognition algorithms are applied depending on the category of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned speech recognition unit, It estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned speech recognition unit, During speech recognition, the recognition priority is determined based on when the audio was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned speech recognition unit, During speech recognition, the recognition order is adjusted based on the relevance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the speech synthesis expression based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned speech synthesis unit, During speech synthesis, the level of detail in the synthesis is adjusted based on the importance of each voice. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned speech synthesis unit, When synthesizing speech, different synthesis algorithms are applied depending on the category of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the length of the synthesized speech based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned speech synthesis unit, During speech synthesis, the synthesis priority is determined based on the timing of speech submission. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned speech synthesis unit, During speech synthesis, the synthesis order is adjusted based on the relevance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way it delivers audio based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected by referring to the user's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing the service, the timing of delivery will be adjusted based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the audio content to be delivered based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing the service, the system analyzes the user's social media activity and provides relevant audio. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 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 unit that collects sound, A speech recognition unit analyzes the audio collected by the aforementioned collection unit and detects noise and interruptions, A speech synthesis unit generates natural speech based on the missing portion detected by the speech recognition unit, The system includes a providing unit that provides the voice generated by the voice synthesis unit to the user. A system characterized by the following features.

2. The aforementioned speech recognition unit, It analyzes the audio during a call in real time to detect noise and interruptions. The system according to feature 1.

3. The aforementioned speech synthesis unit, Based on the missing parts identified by the speech recognition unit, natural-sounding speech is generated. The system according to feature 1.

4. The aforementioned supply unit is, Provides the generated audio to the user in real time. The system according to feature 1.

5. The aforementioned speech recognition unit, Analyze the speech of people with speech difficulties to identify missing parts. The system according to feature 1.

6. The aforementioned speech synthesis unit, Generates natural-sounding speech to complement the speech of people with speech difficulties. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of audio collection based on those emotions. The system according to feature 1.

8. The aforementioned collection unit is When collecting audio, the system analyzes ambient noise and selects the optimal collection method. The system according to feature 1.

Images