system

Abstract

The system according to this embodiment aims to convert speech into a format that is easy to hear and understand in real time. [Solution] The system according to the embodiment comprises an input unit, an analysis unit, a conversion unit, and an output unit. The input unit receives audio input. The analysis unit analyzes the audio input by the input unit. The conversion unit converts the audio analyzed by the analysis unit. The output unit outputs the audio converted by the conversion unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes 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 it is difficult to adjust the ease of listening and understanding of speech in real time.

[0005] The system according to the embodiment aims to convert speech into an easy-to-listen-to and easy-to-understand form in real time.

Means for Solving the Problems

[0006] The system according to the embodiment includes an input unit, an analysis unit, a conversion unit, and an output unit. The input unit inputs speech. The analysis unit analyzes the speech input by the input unit. The conversion unit converts the speech analyzed by the analysis unit. The output unit outputs the speech converted by the conversion unit.

Effects of the Invention

[0007] The system according to this embodiment can convert speech into a format that is easy to hear and understand in real time. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 conversion system according to an embodiment of the present invention is a system that converts speech spoken through an AI microphone into a sound that is easy for the listener to understand in real time. This voice conversion system has the following functions: For example, it has a filler removal function that removes fillers such as coughs, um, and uh. It also has a volume adjustment function that adjusts soft or loud voices to a constant volume. It also has a speaking speed adjustment function that adjusts fast or slow speaking to a constant speed. It also has an articulation and dialect conversion function that converts parts with poor articulation or dialects into standard Japanese. It also has a stumble correction function that automatically corrects parts that are stumbled over during speech. It also has a difficult word replacement function that replaces difficult words and technical terms with simpler words. Furthermore, the settings for the output sound can be changed depending on the situation. For example, for elderly people, the volume can be set to be louder than usual and the speaking speed can be set to be slower. This system improves the quality of communication by analyzing speech in real time using AI and converting it into a sound that is easy for the listener to understand. As a result, the voice conversion system can analyze the speaker's voice in real time and convert it into a sound that is easy for the listener to understand.

[0029] The voice conversion system according to the embodiment comprises an input unit, an analysis unit, a conversion unit, and an output unit. The input unit receives voice input. The input unit can receive voice input using, for example, a microphone. The input unit can also receive voice input by importing an audio file. The analysis unit analyzes the voice input by the input unit. The analysis unit can analyze the voice using, for example, speech recognition technology. The analysis unit can also analyze the voice using acoustic analysis technology. The conversion unit converts the voice analyzed by the analysis unit. The conversion unit can convert the voice using, for example, speech filtering technology. The conversion unit can also convert the voice using speech synthesis technology. The output unit outputs the voice converted by the conversion unit. The output unit can output the voice using, for example, a speaker. The output unit can also output the voice by generating an audio file. As a result, the voice conversion system according to the embodiment can analyze, convert, and output voice in real time, converting it into a sound that is easy for the listener to understand. Some or all of the above-described processes in the analysis unit and conversion unit may be performed using, for example, AI, or without using AI. For example, the analysis unit inputs the audio received by the input unit into an AI model, allowing the AI ​​to perform audio analysis. The conversion unit inputs the audio analyzed by the analysis unit into an AI model, allowing the AI ​​to perform audio conversion.

[0030] The input unit accepts audio input. For example, audio can be input using a microphone. Specifically, using a high-sensitivity condenser microphone or dynamic microphone enables clear, low-noise audio input. The input unit can also accept audio files. Audio file import supports common audio formats such as MP3, WAV, and FLAC, allowing users to easily import existing audio data into the system. Furthermore, the input unit also features the ability to receive audio data wirelessly via Bluetooth® or Wi-Fi, enabling audio input from smartphones and tablets. This provides the input unit with diverse audio input methods, improving user convenience.

[0031] The analysis unit analyzes the audio input by the input unit. For example, the analysis unit can analyze the audio using speech recognition technology. Specifically, speech recognition technology utilizes a deep learning-based speech recognition model to convert audio data into text data. This model is trained using a large amount of audio data and corresponding text data, enabling high-accuracy speech recognition. The analysis unit can also analyze the audio using acoustic analysis technology. Acoustic analysis technology analyzes the frequency components and temporal changes of the audio to extract its characteristics. For example, it can analyze parameters such as pitch, volume, and tempo to gain a detailed understanding of the audio's characteristics. Furthermore, the analysis unit can use noise reduction technology to remove background noise from the input audio, providing clear audio data. This allows the analysis unit to analyze the input audio with high accuracy and provide the information necessary for subsequent processing.

[0032] The conversion unit converts the audio analyzed by the analysis unit. For example, the conversion unit can convert the audio using speech filtering technology. Specifically, speech filtering technology improves the quality of the audio by emphasizing or suppressing specific frequency bands. For example, it can make the audio clearer by emphasizing high frequencies or reduce noise by suppressing low frequencies. The conversion unit can also convert the audio using speech synthesis technology. Speech synthesis technology is a technology that generates new audio based on text data, and can produce audio with natural pronunciation and intonation. Furthermore, the conversion unit can utilize AI-based speech conversion technology to convert the input audio into a different voice quality or speaker characteristics. For example, it can convert a male voice to a female voice or make the voice resemble that of a specific speaker. This allows the conversion unit to meet diverse speech conversion needs and provide the user with the optimal audio.

[0033] The output unit outputs the audio converted by the conversion unit. The output unit can output audio using, for example, a speaker. Specifically, using a high-quality speaker allows for clear and natural audio reproduction. The output unit can also generate and output audio files. Audio file generation supports common audio formats such as MP3, WAV, and FLAC, allowing users to save the converted audio for later playback. Furthermore, the output unit also features wireless audio output via Bluetooth and Wi-Fi, enabling audio transmission to devices such as smartphones, tablets, and wireless speakers. This provides the output unit with diverse audio output options, improving user convenience. Additionally, the output unit includes functions to adjust the audio output level and sound quality, allowing for audio output tailored to user preferences. This enables the output unit to output converted audio in high quality, providing users with an optimal audio experience.

[0034] The filler removal unit can remove fillers. The filler removal unit removes fillers such as coughs, um, and uh. The filler removal unit can detect and remove fillers using speech recognition technology. For example, the filler removal unit can detect fillers using speech recognition technology and remove the filler portion. The filler removal unit can also adjust the beginning and end of the speech to maintain a natural flow when removing fillers. For example, after removing fillers, the filler removal unit adjusts the beginning and end of the speech to maintain a natural flow. This makes the speech sound smoother by removing the fillers. Some or all of the above processing in the filler removal unit may be performed using AI, for example, or without AI. For example, the filler removal unit can remove fillers using an AI model that detects fillers using speech recognition technology and removes the filler portion.

[0035] The volume control unit can adjust the volume. For example, it can adjust quiet or loud voices to a constant volume. The volume control unit can increase or decrease the volume. For example, it can amplify quiet voices and attenuate loud voices. The volume control unit can also maintain a constant volume using normalization technology. For example, it can maintain a constant volume using normalization technology. By maintaining a constant volume, it makes it easier for the listener to hear. Some or all of the above processing in the volume control unit may be performed using AI, for example, or without AI. For example, the volume control unit can input audio data into an AI model and have the AI ​​perform volume increases / decreases or normalization.

[0036] The speed adjustment unit can adjust the speaking speed. For example, it can adjust fast or slow speaking to a constant speed. The speed adjustment unit can increase or decrease the speaking speed. For example, it can slow down fast speaking and speed up slow speaking. The speed adjustment unit can also change the tempo. For example, it can adjust the speaking speed by changing the tempo. This makes it easier for the listener to understand by keeping the speaking speed constant. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into an AI model and have the AI ​​perform the increase or decrease in speaking speed and the change in tempo.

[0037] The conversion unit can convert parts with poor articulation or dialects into standard Japanese. For example, the conversion unit can correct parts with poor articulation and convert dialects into standard Japanese. The conversion unit can also correct phonemes. For example, the conversion unit can correct the phonemes in parts with poor articulation and convert them into standard Japanese. In addition, the conversion unit can replace dialect phonemes with standard Japanese phonemes in order to convert dialects into standard Japanese. For example, the conversion unit replaces dialect phonemes with standard Japanese phonemes and converts them. This makes it easier for the listener to understand by converting articulation and dialects into standard Japanese. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into an AI model and have the AI ​​perform the conversion of parts with poor articulation or dialects.

[0038] The corrective function can automatically correct parts where the speaker has stumbled over their words. For example, the corrective function can detect a part where the speaker has stumbled over their words while speaking and automatically correct it. The corrective function can detect parts where the speaker has stumbled over their words using speech recognition technology. For example, the corrective function can detect a part where the speaker has stumbled over their words using speech recognition technology and repronounce it. In addition, when correcting a part where the speaker has stumbled over their words, the corrective function can adjust the beginning and end of the speech to maintain a natural flow. As a result, the speech sounds smoother because the corrective function automatically corrects parts where the speaker has stumbled over their words. Some or all of the above processing in the corrective function may be performed using AI, for example, or without AI. For example, the corrective function can correct a part where the speaker has stumbled over their words using an AI model that detects and reproduces parts where the speaker has stumbled over their words using speech recognition technology.

[0039] The replacement unit can replace difficult words and technical terms with simpler words. For example, the replacement unit can replace difficult words and technical terms with simpler words. The replacement unit can perform dictionary-based conversion. For example, the replacement unit can refer to a dictionary to replace difficult words and technical terms with simpler words. The replacement unit can also use a thesaurus to search for synonyms and replace them with simpler words. For example, the replacement unit can use a thesaurus to search for synonyms and replace them with simpler words. By replacing difficult words with simpler words, it becomes easier for the listener to understand. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into an AI model and have the AI ​​perform the replacement of difficult words and technical terms.

[0040] The settings change unit can change the settings of the output sound depending on the situation. For example, for elderly people, the settings change unit can set the volume to be louder than usual and the speaking speed to be slower. The settings change unit can have criteria for changing the settings of the sound according to the situation. For example, the settings change unit can change the sound settings according to the situation, such as a meeting, presentation, or telephone conversation. This allows the optimal sound to be provided to the listener by changing the settings of the sound according to the situation. Some or all of the above processing in the settings change unit may be performed using AI, for example, or without using AI. For example, the settings change unit can input the sound settings according to the situation into an AI model and have the AI ​​perform the sound setting changes.

[0041] The input unit can analyze the user's past voice input history and select the optimal input method. For example, if the user has frequently used voice input in the past, the input unit will prioritize suggesting voice input. If the user has frequently used text input in the past, the input unit can also prioritize suggesting text input. The input unit can also suggest the optimal input method for a specific time period based on the user's past input history. In this way, by analyzing past voice input history, the system can provide the user with the most suitable input method. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's past voice input history into an AI model and have the AI ​​select the optimal input method.

[0042] The input unit can filter out the user's current ambient noise during voice input to remove noise. For example, if the user is in a noisy environment, the input unit filters out background noise to make the voice input clearer. If the user is in a quiet environment, the input unit can also optimize the voice input by removing even subtle noise. If the user is making voice input while moving, the input unit can also filter out wind noise and traffic noise to remove noise. By filtering out ambient noise and removing noise, clear voice input becomes possible. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's ambient sound data into a generating AI and have the generating AI perform noise reduction.

[0043] The input unit can prioritize inputting highly relevant speech based on the user's geographical location information during voice input. For example, if the user is in a specific location, the input unit will prioritize processing speech input related to that location. If the user is traveling, the input unit can also prioritize processing speech input related to the travel destination. If the user is at home, the input unit can also prioritize processing speech input related to home. This enables more appropriate voice input by prioritizing the input of highly relevant speech based on geographical location information. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's geographical location information to a generating AI and cause the generating AI to prioritize the input of highly relevant speech.

[0044] The input unit can analyze the user's social media activity during voice input and input relevant voice data. For example, the input unit prioritizes inputting words that the user frequently uses on social media. The input unit can also suggest relevant voice data based on information the user has shared on social media. The input unit can also prioritize processing voice data related to specific topics from the user's social media activity. This allows for the priority input of relevant voice data by analyzing social media activity. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's social media activity data into a generating AI and have the generating AI perform the input of relevant voice data.

[0045] The analysis unit can adjust the level of detail of the analysis based on the importance of the audio during speech analysis. For example, the analysis unit can perform a detailed analysis on important speech inputs to provide highly accurate results. The analysis unit can also perform a standard analysis on general speech inputs to provide results quickly. The analysis unit can also perform a simplified analysis on low-importance speech inputs to provide results efficiently. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input speech data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0046] The analysis unit can apply different analysis algorithms depending on the category of the audio during audio analysis. For example, the analysis unit can apply a natural language processing algorithm to conversational audio to analyze its meaning. The analysis unit can also apply a music analysis algorithm to musical audio to analyze melody and rhythm. The analysis unit can also apply an ambient sound analysis algorithm to ambient sound to analyze noise and background sounds. By applying different analysis algorithms depending on the category of the audio, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI execute the application of an analysis algorithm according to the category.

[0047] The analysis unit can determine the priority of analysis based on the submission date of the audio during audio analysis. For example, the analysis unit can prioritize the analysis of the most recent audio input. The analysis unit can also prioritize the analysis of audio inputs with approaching submission deadlines. The analysis unit can also postpone the analysis of older audio inputs. This allows for efficient analysis by determining the priority of analysis based on the submission date of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform the determination of analysis priority based on the submission date.

[0048] The analysis unit can adjust the order of analysis based on the relevance of the audio during speech analysis. For example, the analysis unit can prioritize the analysis of audio from important meetings. It can also perform standard analysis on audio from everyday conversations. The analysis unit can also postpone the analysis of background noise and other noise. This allows for prioritizing the analysis of important audio by adjusting the order of analysis based on the relevance of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform relevance-based order adjustment of the analysis.

[0049] The conversion unit can adjust the level of detail of the conversion based on the importance of the audio during speech conversion. For example, the conversion unit can perform detailed conversion on important audio to provide highly accurate results. The conversion unit can also perform standard conversion on general audio to provide results quickly. The conversion unit can also perform simple conversion on low-importance audio to provide results efficiently. This allows for efficient speech conversion by adjusting the level of detail of the conversion based on the importance of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform the level of detail adjustment of the conversion.

[0050] The conversion unit can apply different conversion algorithms depending on the category of the audio during speech conversion. For example, the conversion unit can apply a natural language processing algorithm to conversational audio to convert its meaning. The conversion unit can also apply a music conversion algorithm to musical audio to convert melody and rhythm. The conversion unit can also apply an ambient sound conversion algorithm to ambient sound to convert noise and background sounds. By applying different conversion algorithms depending on the category of the audio, more accurate speech conversion becomes possible. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI execute the application of a conversion algorithm according to the category.

[0051] The conversion unit can determine the conversion priority based on the submission date of the audio during speech conversion. For example, the conversion unit can prioritize the conversion of the most recent audio input. It can also prioritize the conversion of audio input with an approaching submission deadline. It can also postpone the conversion of older audio inputs. This allows for efficient speech conversion by determining the conversion priority based on the submission date of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform the determination of conversion priority based on the submission date.

[0052] The conversion unit can adjust the order of conversion based on the relevance of the audio during speech conversion. For example, the conversion unit can prioritize the conversion of audio from important meetings. The conversion unit can also perform standard conversions on audio from everyday conversations. The conversion unit can also postpone the conversion of background noise and other sounds. This allows for prioritizing the conversion of important audio by adjusting the order of conversion based on the relevance of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform relevance-based order adjustments.

[0053] The output unit can adjust the level of detail of the output based on the importance of the audio during audio output. For example, the output unit can provide detailed output for important audio to deliver highly accurate results. The output unit can also provide standard output for general audio to deliver results quickly. The output unit can also provide simplified output for low-importance audio to deliver results efficiently. This allows for efficient audio output by adjusting the level of detail of the output based on the importance of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the output.

[0054] The output unit can apply different output algorithms depending on the category of the audio during audio output. For example, the output unit can apply a natural language processing algorithm to conversational audio and output meaning. The output unit can also apply a music output algorithm to musical audio and output melody and rhythm. The output unit can also apply an ambient sound output algorithm to ambient sounds and output noise and background sounds. By applying different output algorithms depending on the category of the audio, more accurate audio output becomes possible. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI execute the application of an output algorithm according to the category.

[0055] The output unit can determine the output priority based on the submission date of the audio when outputting audio. For example, the output unit can prioritize outputting the most recent audio input. The output unit can also prioritize outputting audio inputs with approaching submission deadlines. The output unit can also postpone outputting older audio inputs. This enables efficient audio output by determining the output priority based on the submission date of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform the determination of output priority based on the submission date.

[0056] The output unit can adjust the output order based on the relevance of the audio during audio output. For example, the output unit can prioritize outputting audio from important meetings. The output unit can also output audio from everyday conversations in a standard manner. The output unit can also postpone outputting background noise and other noise. This allows important audio to be prioritized by adjusting the output order based on the relevance of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform relevance-based output order adjustment.

[0057] The filler removal unit can adjust the level of detail of the removal process based on the importance of the audio during filler removal. For example, the filler removal unit can perform detailed filler removal on important audio to provide highly accurate results. The filler removal unit can also perform standard filler removal on general audio to provide results quickly. The filler removal unit can also perform simple filler removal on low-importance audio to provide results efficiently. This allows for efficient filler removal by adjusting the level of detail of the removal process based on the importance of the audio. Some or all of the above-described processes in the filler removal unit may be performed using AI, for example, or without AI. For example, the filler removal unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the removal process.

[0058] The filler deletion unit can determine the priority of deletion based on the submission date of the audio when deleting fillers. For example, the filler deletion unit can prioritize deleting fillers from the most recent audio input. The filler deletion unit can also prioritize deleting fillers from audio inputs with approaching submission deadlines. The filler deletion unit can also postpone deleting fillers from older audio inputs. This enables efficient filler deletion by determining the priority of deletion based on the submission date of the audio. Some or all of the above processing in the filler deletion unit may be performed using AI, for example, or without AI. For example, the filler deletion unit can input audio data into a generating AI and have the generating AI perform the determination of deletion priorities based on the submission date.

[0059] The volume adjustment unit can adjust the level of detail of the adjustment based on the importance of the audio during volume adjustment. For example, the volume adjustment unit can perform detailed volume adjustments on important audio to provide highly accurate results. The volume adjustment unit can also perform standard volume adjustments on general audio to provide quick results. The volume adjustment unit can also perform simple volume adjustments on low-importance audio to provide efficient results. This enables efficient volume adjustment by adjusting the level of detail of the adjustment based on the importance of the audio. Some or all of the above processing in the volume adjustment unit may be performed using AI, for example, or without AI. For example, the volume adjustment unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0060] The volume adjustment unit can determine the priority of volume adjustments based on the submission date of the audio. For example, the volume adjustment unit can prioritize adjusting the volume of the most recent audio input. It can also prioritize adjusting the volume of audio inputs with approaching submission deadlines. It can also postpone adjusting the volume of older audio inputs. This allows for efficient volume adjustment by determining the priority of adjustments based on the submission date of the audio. Some or all of the above processing in the volume adjustment unit may be performed using AI, for example, or without AI. For example, the volume adjustment unit can input audio data into a generating AI and have the generating AI perform the determination of adjustment priorities based on the submission date.

[0061] The speed adjustment unit can adjust the level of detail of the adjustment based on the importance of the audio during speed adjustment. For example, the speed adjustment unit can perform detailed speed adjustment on important audio to provide highly accurate results. The speed adjustment unit can also perform standard speed adjustment on general audio to provide results quickly. The speed adjustment unit can also perform simple speed adjustment on low-importance audio to provide results efficiently. This enables efficient speed adjustment by adjusting the level of detail of the adjustment based on the importance of the audio. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0062] The speed adjustment unit can determine the priority of adjustments based on the submission date of the audio during the speed adjustment process. For example, the speed adjustment unit can prioritize speed adjustments for the most recent audio input. The speed adjustment unit can also prioritize speed adjustments for audio inputs with approaching submission deadlines. The speed adjustment unit can also postpone speed adjustments for older audio inputs. This enables efficient speed adjustments by determining the priority of adjustments based on the submission date of the audio. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into a generating AI and have the generating AI perform the determination of adjustment priorities based on the submission date.

[0063] The rephrasing unit can adjust the level of detail of the rephrasing based on the importance of the audio during the rephrasing process. For example, the rephrasing unit can perform detailed rephrasing on important audio to provide highly accurate results. The rephrasing unit can also perform standard rephrasing on general audio to provide results quickly. The rephrasing unit can also perform simple rephrasing on low-importance audio to provide results efficiently. This allows for efficient rephrasing by adjusting the level of detail of the rephrasing based on the importance of the audio. Some or all of the above processing in the rephrasing unit may be performed using AI, for example, or without AI. For example, the rephrasing unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the rephrasing.

[0064] The rephrasing unit can determine the priority of rephrasing based on the submission date of the audio. For example, the rephrasing unit can prioritize rephrasing the most recent audio input. It can also prioritize rephrasing audio input with an approaching submission deadline. It can also postpone rephrasing older audio inputs. This allows for efficient rephrasing by determining the priority of rephrasing based on the submission date of the audio. Some or all of the above processing in the rephrasing unit may be performed using AI, for example, or without AI. For example, the rephrasing unit can input audio data into a generating AI and have the generating AI perform the determination of rephrasing priority based on the submission date.

[0065] The replacement unit can adjust the level of detail of the replacement based on the importance of the audio during the replacement process. For example, the replacement unit can perform detailed replacement on important audio to provide highly accurate results. The replacement unit can also perform standard replacement on general audio to provide results quickly. The replacement unit can also perform simple replacement on low-importance audio to provide results efficiently. This allows for efficient replacement by adjusting the level of detail of the replacement based on the importance of the audio. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the replacement.

[0066] The replacement unit can determine the priority of replacements based on the submission date of the audio during the replacement process. For example, the replacement unit can prioritize replacements for the most recent audio input. The replacement unit can also prioritize replacements for audio inputs with approaching submission deadlines. The replacement unit can also postpone replacements for older audio inputs. This allows for efficient replacement by determining the priority of replacements based on the submission date of the audio. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into a generating AI and have the generating AI perform the determination of replacement priorities based on the submission date.

[0067] The configuration change unit can adjust the level of detail of configuration changes based on the importance of the audio when changing settings. For example, the configuration change unit can perform detailed configuration changes for important audio to provide highly accurate results. The configuration change unit can also perform standard configuration changes for general audio to provide results quickly. The configuration change unit can also perform simple configuration changes for low-importance audio to provide results efficiently. This allows for efficient configuration changes by adjusting the level of detail of configuration changes based on the importance of the audio. Some or all of the above processing in the configuration change unit may be performed using AI, for example, or without AI. For example, the configuration change unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the configuration changes.

[0068] The configuration change unit can determine the priority of configuration changes based on the timing of audio submissions when changing settings. For example, the configuration change unit can prioritize configuration changes for the most recent audio input. It can also prioritize configuration changes for audio inputs with approaching submission deadlines. It can also postpone configuration changes for older audio inputs. This allows for efficient configuration changes by determining the priority of configuration changes based on the timing of audio submissions. Some or all of the above-described processes in the configuration change unit may be performed using AI, for example, or without AI. For example, the configuration change unit can input audio data into a generating AI and have the generating AI perform the task of determining the priority of configuration changes based on the submission timing.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The voice conversion system can also include features to customize the user's voice quality. For example, it can convert the user's voice to a lower pitch to give a calmer impression, or to a higher pitch to give a brighter, more energetic impression. Furthermore, it can add an echo effect to the voice to enhance realism. This allows users to customize their voice to their liking and communicate more effectively. Voice quality customization is achieved, for example, by analyzing voice data and emphasizing or attenuating specific frequency bands. This allows the user's voice to be optimized for a variety of situations.

[0071] The speech conversion system can also be equipped with the ability to automatically add background sounds based on the user's speech. For example, if the user is talking about nature, birdsong or wind sounds can be added to the background. If the user is talking about a city, car sounds or the hustle and bustle of people can be added to the background. Furthermore, if the user is seeking a relaxed atmosphere, calming music can be added to the background. This allows for background sounds tailored to the content of the speech, resulting in more immersive communication. The addition of background sounds is performed, for example, using speech data analysis or context recognition technology. This allows for the provision of background sounds that are optimal for the user's speech.

[0072] The voice conversion system can also be equipped with the ability to automatically generate gestures based on the user's speech. For example, if the user says, "Look here," it can generate a pointing gesture. If the user says, "That's a big problem," it can generate a gesture of spreading both hands. Furthermore, if the user says, "Thank you," it can generate a slight bow gesture. This allows for gestures that correspond to the speech content, enabling more visually understandable communication. Gesture generation is performed, for example, using speech data analysis and natural language processing technology. This allows for the provision of gestures that are optimal for the user's speech.

[0073] The speech conversion system can also be equipped with the ability to automatically provide visual aids based on the user's speech. For example, if the user says, "Look at this graph," the corresponding graph can be displayed on the screen. If the user says, "This place is here," a map can be displayed to indicate the location. Furthermore, if the user says, "Refer to this data," relevant data can be displayed. This allows for the provision of visual aids tailored to the user's speech, enabling more easily understood communication. The provision of visual aids is carried out, for example, using speech data analysis and context recognition technology. This allows for the provision of visual aids that are optimally suited to the user's speech.

[0074] The speech conversion system can also be equipped with the ability to automatically search for and provide relevant information based on the user's utterances. For example, if a user says, "Tell me about this product," the system can search for and provide relevant product information. Similarly, if a user says, "What's the weather like here?", the system can search for and provide current weather information. Furthermore, if a user says, "Tell me the details of this event," the system can search for and provide detailed information about the event. This allows for more effective communication by providing relevant information tailored to the user's utterances. The search and provision of relevant information is performed, for example, using speech data analysis or natural language processing technology. This enables the system to provide the most relevant information based on the user's utterances.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The input unit receives audio input. For example, audio can be input using a microphone. Alternatively, audio can be input by importing an audio file. Step 2: The analysis unit analyzes the audio input by the input unit. The analysis unit can analyze the audio using, for example, speech recognition technology. Alternatively, the analysis unit can analyze the audio using acoustic analysis technology. Step 3: The conversion unit converts the audio analyzed by the analysis unit. The conversion unit can convert the audio using, for example, audio filtering technology. Alternatively, the conversion unit can convert the audio using speech synthesis technology. Step 4: The output unit outputs the audio converted by the conversion unit. The output unit can output the audio using, for example, a speaker. Alternatively, the output unit can generate an audio file and output the audio from there.

[0077] (Example of form 2) The voice conversion system according to an embodiment of the present invention is a system that converts speech spoken through an AI microphone into a sound that is easy for the listener to understand in real time. This voice conversion system has the following functions: For example, it has a filler removal function that removes fillers such as coughs, um, and uh. It also has a volume adjustment function that adjusts soft or loud voices to a constant volume. It also has a speaking speed adjustment function that adjusts fast or slow speaking to a constant speed. It also has an articulation and dialect conversion function that converts parts with poor articulation or dialects into standard Japanese. It also has a stumble correction function that automatically corrects parts that are stumbled over during speech. It also has a difficult word replacement function that replaces difficult words and technical terms with simpler words. Furthermore, the settings for the output sound can be changed depending on the situation. For example, for elderly people, the volume can be set to be louder than usual and the speaking speed can be set to be slower. This system improves the quality of communication by analyzing speech in real time using AI and converting it into a sound that is easy for the listener to understand. As a result, the voice conversion system can analyze the speaker's voice in real time and convert it into a sound that is easy for the listener to understand.

[0078] The voice conversion system according to the embodiment comprises an input unit, an analysis unit, a conversion unit, and an output unit. The input unit receives voice input. The input unit can receive voice input using, for example, a microphone. The input unit can also receive voice input by importing an audio file. The analysis unit analyzes the voice input by the input unit. The analysis unit can analyze the voice using, for example, speech recognition technology. The analysis unit can also analyze the voice using acoustic analysis technology. The conversion unit converts the voice analyzed by the analysis unit. The conversion unit can convert the voice using, for example, speech filtering technology. The conversion unit can also convert the voice using speech synthesis technology. The output unit outputs the voice converted by the conversion unit. The output unit can output the voice using, for example, a speaker. The output unit can also output the voice by generating an audio file. As a result, the voice conversion system according to the embodiment can analyze, convert, and output voice in real time, converting it into a sound that is easy for the listener to understand. Some or all of the above-described processes in the analysis unit and conversion unit may be performed using, for example, AI, or without using AI. For example, the analysis unit inputs the audio received by the input unit into an AI model, allowing the AI ​​to perform audio analysis. The conversion unit inputs the audio analyzed by the analysis unit into an AI model, allowing the AI ​​to perform audio conversion.

[0079] The input unit accepts audio input. For example, audio can be input using a microphone. Specifically, using a high-sensitivity condenser microphone or dynamic microphone enables clear, low-noise audio input. The input unit can also input audio by importing audio files. Audio file import supports common audio formats such as MP3, WAV, and FLAC, allowing users to easily import existing audio data into the system. Furthermore, the input unit also has the ability to receive audio data wirelessly via Bluetooth or Wi-Fi, enabling audio input from smartphones and tablets. This provides the input unit with diverse audio input methods, improving user convenience.

[0080] The analysis unit analyzes the audio input by the input unit. For example, the analysis unit can analyze the audio using speech recognition technology. Specifically, speech recognition technology utilizes a deep learning-based speech recognition model to convert audio data into text data. This model is trained using a large amount of audio data and corresponding text data, enabling high-accuracy speech recognition. The analysis unit can also analyze the audio using acoustic analysis technology. Acoustic analysis technology analyzes the frequency components and temporal changes of the audio to extract its characteristics. For example, it can analyze parameters such as pitch, volume, and tempo to gain a detailed understanding of the audio's characteristics. Furthermore, the analysis unit can use noise reduction technology to remove background noise from the input audio, providing clear audio data. This allows the analysis unit to analyze the input audio with high accuracy and provide the information necessary for subsequent processing.

[0081] The conversion unit converts the audio analyzed by the analysis unit. For example, the conversion unit can convert the audio using speech filtering technology. Specifically, speech filtering technology improves the quality of the audio by emphasizing or suppressing specific frequency bands. For example, it can make the audio clearer by emphasizing high frequencies or reduce noise by suppressing low frequencies. The conversion unit can also convert the audio using speech synthesis technology. Speech synthesis technology is a technology that generates new audio based on text data, and can produce audio with natural pronunciation and intonation. Furthermore, the conversion unit can utilize AI-based speech conversion technology to convert the input audio into a different voice quality or speaker characteristics. For example, it can convert a male voice to a female voice or make the voice resemble that of a specific speaker. This allows the conversion unit to meet diverse speech conversion needs and provide the user with the optimal audio.

[0082] The output unit outputs the audio converted by the conversion unit. The output unit can output audio using, for example, a speaker. Specifically, using a high-quality speaker allows for clear and natural audio reproduction. The output unit can also generate and output audio files. Audio file generation supports common audio formats such as MP3, WAV, and FLAC, allowing users to save the converted audio for later playback. Furthermore, the output unit also features wireless audio output via Bluetooth and Wi-Fi, enabling audio transmission to devices such as smartphones, tablets, and wireless speakers. This provides the output unit with diverse audio output options, improving user convenience. Additionally, the output unit includes functions to adjust the audio output level and sound quality, allowing for audio output tailored to user preferences. This enables the output unit to output converted audio in high quality, providing users with an optimal audio experience.

[0083] The filler removal unit can remove fillers. The filler removal unit removes fillers such as coughs, um, and uh. The filler removal unit can detect and remove fillers using speech recognition technology. For example, the filler removal unit can detect fillers using speech recognition technology and remove the filler portion. The filler removal unit can also adjust the beginning and end of the speech to maintain a natural flow when removing fillers. For example, after removing fillers, the filler removal unit adjusts the beginning and end of the speech to maintain a natural flow. This makes the speech sound smoother by removing the fillers. Some or all of the above processing in the filler removal unit may be performed using AI, for example, or without AI. For example, the filler removal unit can remove fillers using an AI model that detects fillers using speech recognition technology and removes the filler portion.

[0084] The volume control unit can adjust the volume. For example, it can adjust quiet or loud voices to a constant volume. The volume control unit can increase or decrease the volume. For example, it can amplify quiet voices and attenuate loud voices. The volume control unit can also maintain a constant volume using normalization technology. For example, it can maintain a constant volume using normalization technology. By maintaining a constant volume, it makes it easier for the listener to hear. Some or all of the above processing in the volume control unit may be performed using AI, for example, or without AI. For example, the volume control unit can input audio data into an AI model and have the AI ​​perform volume increases / decreases or normalization.

[0085] The speed adjustment unit can adjust the speaking speed. For example, it can adjust fast or slow speaking to a constant speed. The speed adjustment unit can increase or decrease the speaking speed. For example, it can slow down fast speaking and speed up slow speaking. The speed adjustment unit can also change the tempo. For example, it can adjust the speaking speed by changing the tempo. This makes it easier for the listener to understand by keeping the speaking speed constant. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into an AI model and have the AI ​​perform the increase or decrease in speaking speed and the change in tempo.

[0086] The conversion unit can convert parts with poor articulation or dialects into standard Japanese. For example, the conversion unit can correct parts with poor articulation and convert dialects into standard Japanese. The conversion unit can also correct phonemes. For example, the conversion unit can correct the phonemes in parts with poor articulation and convert them into standard Japanese. In addition, the conversion unit can replace dialect phonemes with standard Japanese phonemes in order to convert dialects into standard Japanese. For example, the conversion unit replaces dialect phonemes with standard Japanese phonemes and converts them. This makes it easier for the listener to understand by converting articulation and dialects into standard Japanese. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into an AI model and have the AI ​​perform the conversion of parts with poor articulation or dialects.

[0087] The corrective function can automatically correct parts where the speaker has stumbled over their words. For example, the corrective function can detect a part where the speaker has stumbled over their words while speaking and automatically correct it. The corrective function can detect parts where the speaker has stumbled over their words using speech recognition technology. For example, the corrective function can detect a part where the speaker has stumbled over their words using speech recognition technology and repronounce it. In addition, when correcting a part where the speaker has stumbled over their words, the corrective function can adjust the beginning and end of the speech to maintain a natural flow. As a result, the speech sounds smoother because the corrective function automatically corrects parts where the speaker has stumbled over their words. Some or all of the above processing in the corrective function may be performed using AI, for example, or without AI. For example, the corrective function can correct a part where the speaker has stumbled over their words using an AI model that detects and reproduces parts where the speaker has stumbled over their words using speech recognition technology.

[0088] The replacement unit can replace difficult words and technical terms with simpler words. For example, the replacement unit can replace difficult words and technical terms with simpler words. The replacement unit can perform dictionary-based conversion. For example, the replacement unit can refer to a dictionary to replace difficult words and technical terms with simpler words. The replacement unit can also use a thesaurus to search for synonyms and replace them with simpler words. For example, the replacement unit can use a thesaurus to search for synonyms and replace them with simpler words. By replacing difficult words with simpler words, it becomes easier for the listener to understand. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into an AI model and have the AI ​​perform the replacement of difficult words and technical terms.

[0089] The settings change unit can change the settings of the output sound depending on the situation. For example, for elderly people, the settings change unit can set the volume to be louder than usual and the speaking speed to be slower. The settings change unit can have criteria for changing the settings of the sound according to the situation. For example, the settings change unit can change the sound settings according to the situation, such as a meeting, presentation, or telephone conversation. This allows the optimal sound to be provided to the listener by changing the settings of the sound according to the situation. Some or all of the above processing in the settings change unit may be performed using AI, for example, or without using AI. For example, the settings change unit can input the sound settings according to the situation into an AI model and have the AI ​​perform the sound setting changes.

[0090] The input unit can estimate the user's emotions and adjust the timing of voice input based on the estimated emotions. For example, if the user is nervous, the input unit can delay the timing of voice input to help the user relax. If the user is in a hurry, the input unit can also speed up the timing of voice input to accept input quickly. If the user is relaxed, the input unit can accept voice input at a natural timing. This allows for more natural voice input by adjusting the timing of voice input according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the input unit may be performed using AI, or not using AI. For example, the input unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the timing of voice input.

[0091] The input unit can analyze the user's past voice input history and select the optimal input method. For example, if the user has frequently used voice input in the past, the input unit will prioritize suggesting voice input. If the user has frequently used text input in the past, the input unit can also prioritize suggesting text input. The input unit can also suggest the optimal input method for a specific time period based on the user's past input history. In this way, by analyzing past voice input history, the system can provide the user with the most suitable input method. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's past voice input history into an AI model and have the AI ​​select the optimal input method.

[0092] The input unit can filter out the user's current ambient noise during voice input to remove noise. For example, if the user is in a noisy environment, the input unit filters out background noise to make the voice input clearer. If the user is in a quiet environment, the input unit can also optimize the voice input by removing even subtle noise. If the user is making voice input while moving, the input unit can also filter out wind noise and traffic noise to remove noise. By filtering out ambient noise and removing noise, clear voice input becomes possible. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's ambient sound data into a generating AI and have the generating AI perform noise reduction.

[0093] The input unit can estimate the user's emotions and determine the priority of the input voice based on the estimated user emotions. For example, if the user is tense, the input unit will prioritize important voice input. If the user is relaxed, the input unit can also process all voice inputs equally. If the user is in a hurry, the input unit can also prioritize voice input that needs to be processed quickly. This allows for the priority of important voices by determining the priority of voices according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the input unit may be performed using AI, or not using AI. For example, the input unit can input user emotion data into a generative AI and have the generative AI perform the voice priority determination.

[0094] The input unit can prioritize inputting highly relevant speech based on the user's geographical location information during voice input. For example, if the user is in a specific location, the input unit will prioritize processing speech input related to that location. If the user is traveling, the input unit can also prioritize processing speech input related to the travel destination. If the user is at home, the input unit can also prioritize processing speech input related to home. This enables more appropriate voice input by prioritizing the input of highly relevant speech based on geographical location information. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's geographical location information to a generating AI and cause the generating AI to prioritize the input of highly relevant speech.

[0095] The input unit can analyze the user's social media activity during voice input and input relevant voice data. For example, the input unit prioritizes inputting words that the user frequently uses on social media. The input unit can also suggest relevant voice data based on information the user has shared on social media. The input unit can also prioritize processing voice data related to specific topics from the user's social media activity. This allows for the priority input of relevant voice data by analyzing social media activity. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's social media activity data into a generating AI and have the generating AI perform the input of relevant voice data.

[0096] The analysis unit can estimate the user's emotions and adjust the voice analysis method based on the estimated emotions. For example, if the user is nervous, the analysis unit can select a simple analysis method and provide results quickly. If the user is relaxed, the analysis unit can also select a detailed analysis method and provide highly accurate results. If the user is in a hurry, the analysis unit can select a rapid analysis method and provide results immediately. This allows for more appropriate analysis results by adjusting the voice analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the voice analysis method.

[0097] The analysis unit can adjust the level of detail of the analysis based on the importance of the audio during speech analysis. For example, the analysis unit can perform a detailed analysis on important speech inputs to provide highly accurate results. The analysis unit can also perform a standard analysis on general speech inputs to provide results quickly. The analysis unit can also perform a simplified analysis on low-importance speech inputs to provide results efficiently. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input speech data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0098] The analysis unit can apply different analysis algorithms depending on the category of the audio during audio analysis. For example, the analysis unit can apply a natural language processing algorithm to conversational audio to analyze its meaning. The analysis unit can also apply a music analysis algorithm to musical audio to analyze melody and rhythm. The analysis unit can also apply an ambient sound analysis algorithm to ambient sound to analyze noise and background sounds. By applying different analysis algorithms depending on the category of the audio, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI execute the application of an analysis algorithm according to the category.

[0099] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is nervous, the analysis unit can prioritize important voice analysis. If the user is relaxed, the analysis unit can also perform all voice analysis equally. If the user is in a hurry, the analysis unit can also prioritize voices that need to be analyzed quickly. In this way, important analyses can be prioritized by determining the priority of analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the determination of analysis priorities.

[0100] The analysis unit can determine the priority of analysis based on the submission date of the audio during audio analysis. For example, the analysis unit can prioritize the analysis of the most recent audio input. The analysis unit can also prioritize the analysis of audio inputs with approaching submission deadlines. The analysis unit can also postpone the analysis of older audio inputs. This allows for efficient analysis by determining the priority of analysis based on the submission date of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform the determination of analysis priority based on the submission date.

[0101] The analysis unit can adjust the order of analysis based on the relevance of the audio during speech analysis. For example, the analysis unit can prioritize the analysis of audio from important meetings. It can also perform standard analysis on audio from everyday conversations. The analysis unit can also postpone the analysis of background noise and other noise. This allows for prioritizing the analysis of important audio by adjusting the order of analysis based on the relevance of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI and have the generating AI perform relevance-based order adjustment of the analysis.

[0102] The conversion unit can estimate the user's emotions and adjust the speech conversion method based on the estimated emotions. For example, if the user is nervous, the conversion unit can convert the speech in a calm tone. If the user is relaxed, the conversion unit can also convert the speech in a natural tone. If the user is in a hurry, the conversion unit can also convert the speech quickly. This allows for more appropriate speech conversion by adjusting the speech conversion method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversion unit may be performed using AI, for example, or not using AI. For example, the conversion unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the speech conversion method.

[0103] The conversion unit can adjust the level of detail of the conversion based on the importance of the audio during speech conversion. For example, the conversion unit can perform detailed conversion on important audio to provide highly accurate results. The conversion unit can also perform standard conversion on general audio to provide results quickly. The conversion unit can also perform simple conversion on low-importance audio to provide results efficiently. This allows for efficient speech conversion by adjusting the level of detail of the conversion based on the importance of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform the level of detail adjustment of the conversion.

[0104] The conversion unit can apply different conversion algorithms depending on the category of the audio during speech conversion. For example, the conversion unit can apply a natural language processing algorithm to conversational audio to convert its meaning. The conversion unit can also apply a music conversion algorithm to musical audio to convert melody and rhythm. The conversion unit can also apply an ambient sound conversion algorithm to ambient sound to convert noise and background sounds. By applying different conversion algorithms depending on the category of the audio, more accurate speech conversion becomes possible. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI execute the application of a conversion algorithm according to the category.

[0105] The conversion unit can estimate the user's emotions and determine the priority of conversions based on the estimated emotions. For example, if the user is nervous, the conversion unit can prioritize important speech conversions. If the user is relaxed, the conversion unit can also perform all speech conversions equally. If the user is in a hurry, the conversion unit can also prioritize speech that needs to be converted quickly. This allows for the prioritization of important speech by determining the conversion priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversion unit may be performed using AI, or not using AI. For example, the conversion unit can input user emotion data into a generative AI and have the generative AI perform the conversion priority determination.

[0106] The conversion unit can determine the conversion priority based on the submission date of the audio during speech conversion. For example, the conversion unit can prioritize the conversion of the most recent audio input. It can also prioritize the conversion of audio input with an approaching submission deadline. It can also postpone the conversion of older audio inputs. This allows for efficient speech conversion by determining the conversion priority based on the submission date of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform the determination of conversion priority based on the submission date.

[0107] The conversion unit can adjust the order of conversion based on the relevance of the audio during speech conversion. For example, the conversion unit can prioritize the conversion of audio from important meetings. The conversion unit can also perform standard conversions on audio from everyday conversations. The conversion unit can also postpone the conversion of background noise and other sounds. This allows for prioritizing the conversion of important audio by adjusting the order of conversion based on the relevance of the audio. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input audio data into a generating AI and have the generating AI perform relevance-based order adjustments.

[0108] The output unit can estimate the user's emotions and adjust the method of voice output based on the estimated emotions. For example, if the user is tense, the output unit will output voice in a calm tone. If the user is relaxed, the output unit can also output voice in a natural tone. If the user is in a hurry, the output unit can also output voice quickly. This allows for more appropriate voice output by adjusting the method of voice output according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the voice output method.

[0109] The output unit can adjust the level of detail of the output based on the importance of the audio during audio output. For example, the output unit can provide detailed output for important audio to deliver highly accurate results. The output unit can also provide standard output for general audio to deliver results quickly. The output unit can also provide simplified output for low-importance audio to deliver results efficiently. This allows for efficient audio output by adjusting the level of detail of the output based on the importance of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the output.

[0110] The output unit can apply different output algorithms depending on the category of the audio during audio output. For example, the output unit can apply a natural language processing algorithm to conversational audio and output meaning. The output unit can also apply a music output algorithm to musical audio and output melody and rhythm. The output unit can also apply an ambient sound output algorithm to ambient sounds and output noise and background sounds. By applying different output algorithms depending on the category of the audio, more accurate audio output becomes possible. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI execute the application of an output algorithm according to the category.

[0111] The output unit can estimate the user's emotions and determine the priority of output based on the estimated emotions. For example, if the user is tense, the output unit may prioritize important audio output. If the user is relaxed, the output unit may also output all audio equally. If the user is in a hurry, the output unit may also prioritize audio that needs to be output quickly. In this way, important audio can be prioritized by determining the priority of output according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, for example, or not using AI. For example, the output unit can input user emotion data into the generative AI and have the generative AI perform the output priority determination.

[0112] The output unit can determine the output priority based on the submission date of the audio when outputting audio. For example, the output unit can prioritize outputting the most recent audio input. The output unit can also prioritize outputting audio inputs with approaching submission deadlines. The output unit can also postpone outputting older audio inputs. This enables efficient audio output by determining the output priority based on the submission date of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform the determination of output priority based on the submission date.

[0113] The output unit can adjust the output order based on the relevance of the audio during audio output. For example, the output unit can prioritize outputting audio from important meetings. The output unit can also output audio from everyday conversations in a standard manner. The output unit can also postpone outputting background noise and other noise. This allows important audio to be prioritized by adjusting the output order based on the relevance of the audio. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audio data into a generating AI and have the generating AI perform relevance-based output order adjustment.

[0114] The filler removal unit can estimate the user's emotions and adjust the filler removal method based on the estimated emotions. For example, if the user is tense, the filler removal unit can quickly remove fillers to provide smooth audio. If the user is relaxed, the filler removal unit can also remove fillers at a natural pace. If the user is in a hurry, the filler removal unit can quickly remove fillers and provide immediate results. This allows for more appropriate filler removal by adjusting the filler removal method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filler removal unit may be performed using AI or not. For example, the filler removal unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the filler removal method.

[0115] The filler removal unit can adjust the level of detail of the removal process based on the importance of the audio during filler removal. For example, the filler removal unit can perform detailed filler removal on important audio to provide highly accurate results. The filler removal unit can also perform standard filler removal on general audio to provide results quickly. The filler removal unit can also perform simple filler removal on low-importance audio to provide results efficiently. This allows for efficient filler removal by adjusting the level of detail of the removal process based on the importance of the audio. Some or all of the above-described processes in the filler removal unit may be performed using AI, for example, or without AI. For example, the filler removal unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the removal process.

[0116] The filler removal unit can estimate the user's emotions and determine the priority of filler removal based on the estimated emotions. For example, if the user is stressed, the filler removal unit may prioritize the removal of important fillers. If the user is relaxed, the filler removal unit may also remove all fillers equally. If the user is in a hurry, the filler removal unit may also prioritize the removal of fillers that need to be removed quickly. This allows for the priority removal of important fillers by determining the priority of filler removal according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filler removal unit may be performed using AI or not using AI. For example, the filler removal unit can input user emotion data into the generative AI and have the generative AI perform the priority determination of filler removal.

[0117] The filler deletion unit can determine the priority of deletion based on the submission date of the audio when deleting fillers. For example, the filler deletion unit can prioritize deleting fillers from the most recent audio input. The filler deletion unit can also prioritize deleting fillers from audio inputs with approaching submission deadlines. The filler deletion unit can also postpone deleting fillers from older audio inputs. This enables efficient filler deletion by determining the priority of deletion based on the submission date of the audio. Some or all of the above processing in the filler deletion unit may be performed using AI, for example, or without AI. For example, the filler deletion unit can input audio data into a generating AI and have the generating AI perform the determination of deletion priorities based on the submission date.

[0118] The volume control unit can estimate the user's emotions and adjust the volume control method based on the estimated emotions. For example, if the user is tense, the volume control unit can adjust the volume to a calm tone. If the user is relaxed, the volume control unit can also adjust the volume to a natural level. If the user is in a hurry, the volume control unit can adjust the volume quickly. This allows for more appropriate volume control by adjusting the volume control method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the volume control unit may be performed using AI, or not using AI. For example, the volume control unit can input user emotion data into a generative AI and have the generative AI perform the volume control method adjustment.

[0119] The volume adjustment unit can adjust the level of detail of the adjustment based on the importance of the audio during volume adjustment. For example, the volume adjustment unit can perform detailed volume adjustments on important audio to provide highly accurate results. The volume adjustment unit can also perform standard volume adjustments on general audio to provide quick results. The volume adjustment unit can also perform simple volume adjustments on low-importance audio to provide efficient results. This enables efficient volume adjustment by adjusting the level of detail of the adjustment based on the importance of the audio. Some or all of the above processing in the volume adjustment unit may be performed using AI, for example, or without AI. For example, the volume adjustment unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0120] The volume control unit can estimate the user's emotions and determine the priority of volume adjustments based on the estimated emotions. For example, if the user is tense, the volume control unit may prioritize adjusting important volumes. If the user is relaxed, the volume control unit may adjust all volumes equally. If the user is in a hurry, the volume control unit may prioritize adjusting volumes that need to be adjusted quickly. This allows for prioritizing important sounds by determining the priority of volume adjustments according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the volume control unit may be performed using AI or not using AI. For example, the volume control unit can input user emotion data into a generative AI and have the generative AI perform the determination of volume adjustment priorities.

[0121] The volume adjustment unit can determine the priority of volume adjustments based on the submission date of the audio. For example, the volume adjustment unit can prioritize adjusting the volume of the most recent audio input. It can also prioritize adjusting the volume of audio inputs with approaching submission deadlines. It can also postpone adjusting the volume of older audio inputs. This allows for efficient volume adjustment by determining the priority of adjustments based on the submission date of the audio. Some or all of the above processing in the volume adjustment unit may be performed using AI, for example, or without AI. For example, the volume adjustment unit can input audio data into a generating AI and have the generating AI perform the determination of adjustment priorities based on the submission date.

[0122] The speed adjustment unit can estimate the user's emotions and adjust the speed adjustment method based on the estimated user emotions. For example, if the user is nervous, the speed adjustment unit can adjust the speaking speed to a calm pace. If the user is relaxed, the speed adjustment unit can also adjust to a natural speed. If the user is in a hurry, the speed adjustment unit can also adjust the speed quickly. This allows for more appropriate speed adjustment by adjusting the speed adjustment method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input user emotion data into the generative AI and have the generative AI perform the speed adjustment method adjustment.

[0123] The speed adjustment unit can adjust the level of detail of the adjustment based on the importance of the audio during speed adjustment. For example, the speed adjustment unit can perform detailed speed adjustment on important audio to provide highly accurate results. The speed adjustment unit can also perform standard speed adjustment on general audio to provide results quickly. The speed adjustment unit can also perform simple speed adjustment on low-importance audio to provide results efficiently. This enables efficient speed adjustment by adjusting the level of detail of the adjustment based on the importance of the audio. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0124] The speed adjustment unit can estimate the user's emotions and determine the priority of speed adjustments based on the estimated emotions. For example, if the user is tense, the speed adjustment unit will prioritize important speed adjustments. If the user is relaxed, the speed adjustment unit can also adjust all speeds equally. If the user is in a hurry, the speed adjustment unit can also prioritize speeds that need to be adjusted quickly. This allows important audio to be prioritized by determining the priority of speed adjustments according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speed adjustment unit may be performed using AI or not using AI. For example, the speed adjustment unit can input user emotion data into the generative AI and have the generative AI perform the speed adjustment priority determination.

[0125] The speed adjustment unit can determine the priority of adjustments based on the submission date of the audio during the speed adjustment process. For example, the speed adjustment unit can prioritize speed adjustments for the most recent audio input. The speed adjustment unit can also prioritize speed adjustments for audio inputs with approaching submission deadlines. The speed adjustment unit can also postpone speed adjustments for older audio inputs. This enables efficient speed adjustments by determining the priority of adjustments based on the submission date of the audio. Some or all of the above processing in the speed adjustment unit may be performed using AI, for example, or without AI. For example, the speed adjustment unit can input audio data into a generating AI and have the generating AI perform the determination of adjustment priorities based on the submission date.

[0126] The rephrasing unit can estimate the user's emotions and adjust its rephrasing method based on the estimated emotions. For example, if the user is nervous, the rephrasing unit will rephrase in a calm tone. If the user is relaxed, the rephrasing unit can also rephrase in a natural tone. If the user is in a hurry, the rephrasing unit can rephrase quickly. This allows for more appropriate rephrasing by adjusting the rephrasing method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the rephrasing unit may be performed using AI or not. For example, the rephrasing unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the rephrasing method.

[0127] The rephrasing unit can adjust the level of detail of the rephrasing based on the importance of the audio during the rephrasing process. For example, the rephrasing unit can perform detailed rephrasing on important audio to provide highly accurate results. The rephrasing unit can also perform standard rephrasing on general audio to provide results quickly. The rephrasing unit can also perform simple rephrasing on low-importance audio to provide results efficiently. This allows for efficient rephrasing by adjusting the level of detail of the rephrasing based on the importance of the audio. Some or all of the above processing in the rephrasing unit may be performed using AI, for example, or without AI. For example, the rephrasing unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the rephrasing.

[0128] The rephrasing unit can estimate the user's emotions and determine the priority of rephrasing based on the estimated emotions. For example, if the user is nervous, the rephrasing unit may prioritize important rephrasing. If the user is relaxed, the rephrasing unit may also prioritize all rephrasing equally. If the user is in a hurry, the rephrasing unit may also prioritize rephrasing speech that needs to be quickly rephrased. This allows important speech to be prioritized for rephrasing by determining the priority of rephrasing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the rephrasing unit may be performed using AI or not using AI. For example, the rephrasing unit can input user emotion data into the generative AI and have the generative AI perform the determination of rephrasing priority.

[0129] The rephrasing unit can determine the priority of rephrasing based on the submission date of the audio. For example, the rephrasing unit can prioritize rephrasing the most recent audio input. It can also prioritize rephrasing audio input with an approaching submission deadline. It can also postpone rephrasing older audio inputs. This allows for efficient rephrasing by determining the priority of rephrasing based on the submission date of the audio. Some or all of the above processing in the rephrasing unit may be performed using AI, for example, or without AI. For example, the rephrasing unit can input audio data into a generating AI and have the generating AI perform the determination of rephrasing priority based on the submission date.

[0130] The substitution unit can estimate the user's emotions and adjust the substitution method based on the estimated emotions. For example, if the user is nervous, the substitution unit will replace the explanation with simpler words. If the user is relaxed, the substitution unit may replace the explanation with words that include more detail. If the user is in a hurry, the substitution unit may replace the explanation with words that can be quickly understood. This allows for more appropriate substitutions by adjusting the substitution method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the substitution unit may be performed using AI or not using AI. For example, the substitution unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the substitution method.

[0131] The replacement unit can adjust the level of detail of the replacement based on the importance of the audio during the replacement process. For example, the replacement unit can perform detailed replacement on important audio to provide highly accurate results. The replacement unit can also perform standard replacement on general audio to provide results quickly. The replacement unit can also perform simple replacement on low-importance audio to provide results efficiently. This allows for efficient replacement by adjusting the level of detail of the replacement based on the importance of the audio. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the replacement.

[0132] The replacement unit can estimate the user's emotions and determine replacement priorities based on the estimated emotions. For example, if the user is tense, the replacement unit will prioritize important replacements. If the user is relaxed, the replacement unit can also perform all replacements equally. If the user is in a hurry, the replacement unit can also prioritize replacing sounds that need to be replaced quickly. This allows for the priority of replacing important sounds by determining replacement priorities 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 may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the replacement unit may be performed using AI or not. For example, the replacement unit can input user emotion data into a generative AI and have the generative AI perform the replacement priority determination.

[0133] The replacement unit can determine the priority of replacements based on the submission date of the audio during the replacement process. For example, the replacement unit can prioritize replacements for the most recent audio input. The replacement unit can also prioritize replacements for audio inputs with approaching submission deadlines. The replacement unit can also postpone replacements for older audio inputs. This allows for efficient replacement by determining the priority of replacements based on the submission date of the audio. Some or all of the above processing in the replacement unit may be performed using AI, for example, or without AI. For example, the replacement unit can input audio data into a generating AI and have the generating AI perform the determination of replacement priorities based on the submission date.

[0134] The settings change unit can estimate the user's emotions and adjust the method of changing settings based on the estimated emotions. For example, if the user is nervous, the settings change unit can suggest simple settings changes. If the user is relaxed, the settings change unit can also suggest more detailed settings changes. If the user is in a hurry, the settings change unit can also make settings changes quickly. This allows for more appropriate settings changes by adjusting the method of changing settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the settings change unit may be performed using AI or not using AI. For example, the settings change unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the setting change method.

[0135] The configuration change unit can adjust the level of detail of configuration changes based on the importance of the audio when changing settings. For example, the configuration change unit can perform detailed configuration changes for important audio to provide highly accurate results. The configuration change unit can also perform standard configuration changes for general audio to provide results quickly. The configuration change unit can also perform simple configuration changes for low-importance audio to provide results efficiently. This allows for efficient configuration changes by adjusting the level of detail of configuration changes based on the importance of the audio. Some or all of the above processing in the configuration change unit may be performed using AI, for example, or without AI. For example, the configuration change unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail of the configuration changes.

[0136] The settings change unit can estimate the user's emotions and determine the priority of settings changes based on the estimated emotions. For example, if the user is stressed, the settings change unit will prioritize important settings changes. If the user is relaxed, the settings change unit can also make all settings changes evenly. If the user is in a hurry, the settings change unit can make settings changes quickly. This allows for prioritizing important settings changes by determining the priority of settings changes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the settings change unit may be performed using AI or not using AI. For example, the settings change unit can input user emotion data into a generative AI and have the generative AI perform the determination of settings change priorities.

[0137] The configuration change unit can determine the priority of configuration changes based on the timing of audio submissions when changing settings. For example, the configuration change unit can prioritize configuration changes for the most recent audio input. It can also prioritize configuration changes for audio inputs with approaching submission deadlines. It can also postpone configuration changes for older audio inputs. This allows for efficient configuration changes by determining the priority of configuration changes based on the timing of audio submissions. Some or all of the above-described processes in the configuration change unit may be performed using AI, for example, or without AI. For example, the configuration change unit can input audio data into a generating AI and have the generating AI perform the task of determining the priority of configuration changes based on the submission timing.

[0138] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0139] The voice conversion system can also include features to customize the user's voice quality. For example, it can convert the user's voice to a lower pitch to give a calmer impression, or to a higher pitch to give a brighter, more energetic impression. Furthermore, it can add an echo effect to the voice to enhance realism. This allows users to customize their voice to their liking and communicate more effectively. Voice quality customization is achieved, for example, by analyzing voice data and emphasizing or attenuating specific frequency bands. This allows the user's voice to be optimized for a variety of situations.

[0140] The voice conversion system can also be equipped with the ability to estimate the user's emotions and adjust the tone of voice based on those emotions. For example, if the user is nervous, the tone of voice can be adjusted to be calmer. If the user is happy, the tone of voice can be made brighter. Furthermore, if the user is sad, the tone of voice can be made gentler. This allows for the provision of a voice tone that matches the user's emotions, enabling more natural communication. Emotion estimation is performed, for example, using voice data analysis or facial recognition technology. This allows for the provision of the optimal voice tone according to the user's emotions.

[0141] The speech conversion system can also be equipped with the ability to automatically add background sounds based on the user's speech. For example, if the user is talking about nature, birdsong or wind sounds can be added to the background. If the user is talking about a city, car sounds or the hustle and bustle of people can be added to the background. Furthermore, if the user is seeking a relaxed atmosphere, calming music can be added to the background. This allows for background sounds tailored to the content of the speech, resulting in more immersive communication. The addition of background sounds is performed, for example, using speech data analysis or context recognition technology. This allows for the provision of background sounds that are optimal for the user's speech.

[0142] The voice conversion system can also be equipped with the ability to estimate the user's emotions and automatically adjust the content of speech based on those emotions. For example, if the user is nervous, the speech can be made concise and easy to understand. If the user is relaxed, the speech can be made more detailed and informative. Furthermore, if the user is in a hurry, the speech can be shortened to convey the message quickly. This allows for the provision of optimal speech content tailored to the user's emotions, resulting in more effective communication. Emotion estimation is performed, for example, by analyzing voice data or using biosensors. This enables the provision of optimal speech content tailored to the user's emotions.

[0143] The voice conversion system can also be equipped with the ability to automatically generate gestures based on the user's speech. For example, if the user says, "Look here," it can generate a pointing gesture. If the user says, "That's a big problem," it can generate a gesture of spreading both hands. Furthermore, if the user says, "Thank you," it can generate a slight bow gesture. This allows for gestures that correspond to the speech content, enabling more visually understandable communication. Gesture generation is performed, for example, using speech data analysis and natural language processing technology. This allows for the provision of gestures that are optimal for the user's speech.

[0144] The voice conversion system can also be equipped with the ability to estimate the user's emotions and automatically adjust the speaking pace based on those emotions. For example, if the user is nervous, the speaking pace can be slowed down to help them relax. If the user is relaxed, they can speak at a natural pace. Furthermore, if the user is in a hurry, the speaking pace can be sped up to convey information quickly. This allows for the provision of an optimal speaking pace tailored to the user's emotions, leading to more effective communication. Emotion estimation is performed, for example, by analyzing voice data or using biosensors. This enables the provision of an optimal speaking pace tailored to the user's emotions.

[0145] The speech conversion system can also be equipped with the ability to automatically provide visual aids based on the user's speech. For example, if the user says, "Look at this graph," the corresponding graph can be displayed on the screen. If the user says, "This place is here," a map can be displayed to indicate the location. Furthermore, if the user says, "Refer to this data," relevant data can be displayed. This allows for the provision of visual aids tailored to the user's speech, enabling more easily understood communication. The provision of visual aids is carried out, for example, using speech data analysis and context recognition technology. This allows for the provision of visual aids that are optimally suited to the user's speech.

[0146] The voice conversion system can also be equipped with the ability to estimate the user's emotions and automatically adjust the content of their speech based on those emotions. For example, if the user is nervous, the speech can be made concise and easy to understand. If the user is relaxed, the speech can be made more detailed and informative. Furthermore, if the user is in a hurry, the speech can be shortened to convey the message quickly. This allows for the provision of optimal speech content tailored to the user's emotions, resulting in more effective communication. Emotion estimation is performed, for example, by analyzing voice data or using biosensors. This enables the provision of optimal speech content tailored to the user's emotions.

[0147] The speech conversion system can also be equipped with the ability to automatically search for and provide relevant information based on the user's utterances. For example, if a user says, "Tell me about this product," the system can search for and provide relevant product information. Similarly, if a user says, "What's the weather like here?", the system can search for and provide current weather information. Furthermore, if a user says, "Tell me the details of this event," the system can search for and provide detailed information about the event. This allows for more effective communication by providing relevant information tailored to the user's utterances. The search and provision of relevant information is performed, for example, using speech data analysis or natural language processing technology. This enables the system to provide the most relevant information based on the user's utterances.

[0148] The voice conversion system can also be equipped with the ability to estimate the user's emotions and automatically adjust the content of their speech based on those emotions. For example, if the user is nervous, the speech can be made concise and easy to understand. If the user is relaxed, the speech can be made more detailed and informative. Furthermore, if the user is in a hurry, the speech can be shortened to convey the message quickly. This allows for the provision of optimal speech content tailored to the user's emotions, resulting in more effective communication. Emotion estimation is performed, for example, by analyzing voice data or using biosensors. This enables the provision of optimal speech content tailored to the user's emotions.

[0149] The following briefly describes the processing flow for example form 2.

[0150] Step 1: The input unit receives audio input. For example, audio can be input using a microphone. Alternatively, audio can be input by importing an audio file. Step 2: The analysis unit analyzes the audio input by the input unit. The analysis unit can analyze the audio using, for example, speech recognition technology. Alternatively, the analysis unit can analyze the audio using acoustic analysis technology. Step 3: The conversion unit converts the audio analyzed by the analysis unit. The conversion unit can convert the audio using, for example, audio filtering technology. Alternatively, the conversion unit can convert the audio using speech synthesis technology. Step 4: The output unit outputs the audio converted by the conversion unit. The output unit can output the audio using, for example, a speaker. Alternatively, the output unit can generate an audio file and output the audio from there.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the input unit, analysis unit, conversion unit, and output unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the input unit can input audio using the microphone 38B of the smart device 14. The analysis unit can analyze the audio using the specific processing unit 290 of the data processing unit 12. The conversion unit can convert the audio using the specific processing unit 290 of the data processing unit 12. The output unit can output audio using the speaker 40B 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 can be modified in various ways.

[0155] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] Each of the multiple elements described above, including the input unit, analysis unit, conversion unit, and output unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the input unit can input sound using the microphone 238 of the smart glasses 214. The analysis unit can analyze the sound using the specific processing unit 290 of the data processing unit 12. The conversion unit can convert the sound using the specific processing unit 290 of the data processing unit 12. The output unit can output sound using the speaker 240 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.

[0171] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] Each of the multiple elements described above, including the input unit, analysis unit, conversion unit, and output unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the input unit can input audio using the microphone 238 of the headset terminal 314. The analysis unit can analyze the audio using the specific processing unit 290 of the data processing unit 12. The conversion unit can convert the audio using the specific processing unit 290 of the data processing unit 12. The output unit can output audio using the speaker 240 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.

[0187] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] Each of the multiple elements described above, including the input unit, analysis unit, conversion unit, and output unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the input unit can input sound using the microphone 238 of the robot 414. The analysis unit can analyze the sound using the specific processing unit 290 of the data processing unit 12. The conversion unit can convert the sound using the specific processing unit 290 of the data processing unit 12. The output unit can output sound using the speaker 240 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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."

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] (Note 1) The input section for voice input, An analysis unit that analyzes the audio input by the aforementioned input unit, A conversion unit that converts the audio analyzed by the aforementioned analysis unit, An output unit that outputs the audio converted by the conversion unit, Equipped with A system characterized by the following features. (Note 2) It includes a filler removal unit for removing fillers. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a volume control unit for adjusting the volume. The system described in Appendix 1, characterized by the features described herein. (Note 4) It features a speed adjustment unit to adjust the speaking speed. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a translation unit that converts parts with poor articulation or dialects into standard Japanese. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a correction function that automatically corrects the part that was stumbled over. The system described in Appendix 1, characterized by the features described herein. (Note 7) It includes a replacement function that replaces difficult words and technical terms with simpler words. The system described in Appendix 1, characterized by the features described herein. (Note 8) It includes a setting change section that allows you to change the settings of the sound output depending on the situation. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned input unit is It estimates the user's emotions and adjusts the timing of voice input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned input unit is The system analyzes the user's past voice input history and selects the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned input unit is When using voice input, the system filters out the user's current ambient noise to remove unwanted sounds. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned input unit is It estimates the user's emotions and determines the priority of voice input based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned input unit is During voice input, the system prioritizes input of highly relevant voice data based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned input unit is During voice input, the system analyzes the user's social media activity and inputs relevant voice data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the voice analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During voice analysis, the level of detail of the analysis is adjusted based on the importance of the voice. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During audio analysis, different analysis algorithms are applied depending on the category of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During audio analysis, the analysis priority is determined based on when the audio was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During audio analysis, the order of analysis is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 21) The conversion unit is It estimates the user's emotions and adjusts the speech conversion method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The conversion unit is During speech conversion, the level of detail of the conversion is adjusted based on the importance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 23) The conversion unit is During speech conversion, different conversion algorithms are applied depending on the category of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 24) The conversion unit is It estimates the user's emotions and determines the priority of conversions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The conversion unit is During speech conversion, the conversion priority is determined based on when the audio was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 26) The conversion unit is During speech conversion, the order of conversion is adjusted based on the relevance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 27) The output unit is, It estimates the user's emotions and adjusts the voice output method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The output unit is, When outputting audio, adjust the level of detail based on the importance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 29) The output unit is, When outputting audio, different output algorithms are applied depending on the audio category. The system described in Appendix 1, characterized by the features described herein. (Note 30) The output unit is, It estimates the user's emotions and determines the priority of the output based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The output unit is, When outputting audio, the output priority is determined based on when the audio was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 32) The output unit is, When outputting audio, the output order is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 33) The filler removal unit is, The system estimates the user's emotions and adjusts the filler removal method based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The filler removal unit is, When removing fillers, adjust the level of detail of the removal based on the importance of the audio. The system described in Appendix 2, characterized by the features described herein. (Note 35) The filler removal unit is, The system estimates the user's emotions and determines the priority of filler removal based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The filler removal unit is, When deleting fillers, the priority of deletion is determined based on when the audio was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 37) The volume control unit is, It estimates the user's emotions and adjusts the volume control method based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The volume control unit is, When adjusting the volume, the level of detail of the adjustment is adjusted based on the importance of the audio. The system described in Appendix 3, characterized by the features described herein. (Note 39) The volume control unit is, It estimates the user's emotions and determines the priority of volume adjustments based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The volume control unit is, When adjusting the volume, the priority of adjustments is determined based on when the audio was submitted. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned speed adjustment unit is It estimates the user's emotions and adjusts the speed adjustment method based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned speed adjustment unit is When adjusting the speed, the level of detail of the adjustment is adjusted based on the importance of the audio. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned speed adjustment unit is Estimate the user's emotion and determine the priority of speed adjustment based on the estimated user emotion The system according to appended note 4, characterized by the above (Appended note 44) The speed adjustment unit When adjusting the speed, determine the priority of adjustment based on the voice submission time The system according to appended note 4, characterized by the above (Appended note 45) The paraphrasing unit Estimate the user's emotion and adjust the paraphrasing method based on the estimated user emotion The system according to appended note 6, characterized by the above (Appended note 46) The paraphrasing unit When paraphrasing, adjust the detail level of paraphrasing based on the importance of the voice The system according to appended note 6, characterized by the above (Appended note 47) The paraphrasing unit Estimate the user's emotion and determine the priority of paraphrasing based on the estimated user emotion The system according to appended note 6, characterized by the above (Appended note 48) The paraphrasing unit When paraphrasing, determine the priority of paraphrasing based on the voice submission time The system according to appended note 6, characterized by the above (Appended note 49) The replacement unit Estimate the user's emotion and adjust the replacement method based on the estimated user emotion The system according to appended note 7, characterized by the above (Appended note 50) The replacement unit When replacing, adjust the detail level of replacement based on the importance of the voice The system according to appended note 7, characterized by the above (Appended note 51) The replacement unit It estimates the user's emotions and determines replacement priorities based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 52) The aforementioned replacement part is, When replacing audio files, the priority of replacements is determined based on when the audio files were submitted. The system described in Appendix 7, characterized by the features described herein. (Note 53) The aforementioned setting change unit is It estimates the user's emotions and adjusts how settings are changed based on those estimated emotions. The system described in Appendix 8, characterized by the features described herein. (Note 54) The aforementioned setting change unit is, When changing settings, adjust the level of detail of the setting change based on the importance of the audio. The system described in Appendix 8, characterized by the features described herein. (Note 55) The aforementioned setting change unit is, It estimates the user's emotions and determines the priority of setting changes based on the estimated user emotions. The system described in Appendix 8, characterized by the features described herein. (Note 56) The aforementioned setting change unit is When changing settings, the priority of the setting change is determined based on when the audio was submitted. The system described in Appendix 8, characterized by the features described herein. [Explanation of Symbols]

[0223] 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. The input section for voice input, An analysis unit that analyzes the audio input by the aforementioned input unit, A conversion unit that converts the audio analyzed by the aforementioned analysis unit, An output unit that outputs the audio converted by the conversion unit, Equipped with A system characterized by the following features.

2. It includes a filler removal unit for removing fillers. The system according to feature 1.

3. It has a volume control unit for adjusting the volume. The system according to feature 1.

4. It features a speed adjustment unit to adjust the speaking speed. The system according to feature 1.

5. The conversion unit is Translate parts with poor articulation or dialect into standard Japanese. The system according to feature 1.

6. It includes a correction function that automatically corrects the part that was stumbled over. The system according to feature 1.

7. It includes a replacement function that replaces difficult words and technical terms with simpler words. The system according to feature 1.

8. It includes a setting change section that allows you to change the settings of the sound output depending on the situation. The system according to feature 1.

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

10. The aforementioned input unit is The system analyzes the user's past voice input history and selects the optimal input method. The system according to feature 1.

Images