system

Abstract

The system according to this embodiment aims to enable visually impaired or bedridden people to enjoy video content. [Solution] The system according to the embodiment comprises an acquisition unit, an analysis unit, a language conversion unit, a speech conversion unit, and a provision unit. The acquisition unit acquires auditory information from video content. The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. The language conversion unit translates the visual information analyzed by the analysis unit into language. The speech conversion unit converts the visual information translated by the language conversion unit into speech. The provision unit provides audio content by combining the speech converted by the speech conversion unit with the auditory information.

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 performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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 for visually impaired people or bedridden people to enjoy video content.

[0005] The system according to the embodiment aims to enable visually impaired people or bedridden people to enjoy video content.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an analysis unit, a language conversion unit, a speech conversion unit, and a provision unit. The acquisition unit acquires auditory information from video content. The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. The language conversion unit translates the visual information analyzed by the analysis unit into language. The speech conversion unit converts the visual information translated by the language conversion unit into speech. The provision unit provides audio content by combining the speech converted by the speech conversion unit with the auditory information. [Effects of the Invention]

[0007] The system according to this embodiment can enable visually impaired or bedridden people to enjoy video content. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example of form 1) An audio content creation system according to an embodiment of the present invention is a system that acquires auditory information from video content, and a generating AI analyzes the visual information contained in the video, verbalizes it, and converts it into speech. This audio content creation system is intended for visually impaired or bedridden people to enjoy video content such as movies and dramas. The audio content creation system acquires auditory information such as dialogue, music, and sound effects from the video content. Next, the generating AI analyzes the visual information contained in the video and verbalizes the facial expressions of the characters and the scenery. For example, it verbalizes visual information such as "She looked down shyly" or "In a small park in the middle of a big city." Next, it converts the verbalized visual information into speech. At this time, the generating AI can read the visual information aloud in a natural voice. For example, it provides visual information such as "She looked down shyly" as speech. Finally, it combines auditory information such as dialogue, music, and sound effects with the verbalized visual information to create audio content. For example, the audio content creation system is intended for visually impaired or bedridden people to enjoy video content such as movies and dramas. For example, it can provide audio content with commentary through a streaming service. This makes it possible for everyone to enjoy video content. This means that audio content creation systems can allow visually impaired or bedridden people to enjoy video content such as movies and dramas.

[0029] The audio content creation system according to this embodiment comprises an acquisition unit, an analysis unit, a language conversion unit, a speech conversion unit, and a provision unit. The acquisition unit acquires auditory information from video content. The acquisition unit can acquire auditory information such as dialogue, music, and sound effects from video content. The acquisition unit collects audio using a microphone, for example. The acquisition unit can also directly extract auditory information from the audio track of video content. Furthermore, the acquisition unit can convert the audio of video content into text data using speech recognition technology. The analysis unit analyzes visual information contained in the video based on the auditory information acquired by the acquisition unit. The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video, for example. The analysis unit analyzes the facial expressions of characters using face recognition technology, for example. The analysis unit can also analyze the scenery using scene analysis technology. Furthermore, the analysis unit can identify objects in the video using object recognition technology. The language conversion unit translates the visual information analyzed by the analysis unit into language. The language processing unit can, for example, convert visual information into text data using natural language processing technology. The language processing unit can convert visual information into natural language using, for example, text generation AI. The language processing unit can also use algorithms to generate grammatically correct sentences. Furthermore, the language processing unit can use techniques to generate semantically consistent sentences. The speech conversion unit converts the visual information languaged by the language processing unit into speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. The speech conversion unit can, for example, generate natural speech using speech synthesis AI. Furthermore, the speech conversion unit can use techniques to adjust intonation and accent. Furthermore, the speech conversion unit can use algorithms to improve speech fluency. The delivery unit combines the speech converted by the speech conversion unit with auditory information to provide audio content. The delivery unit can, for example, provide audio content through streaming services. The delivery unit can, for example, distribute audio content through web applications or mobile applications.Furthermore, the distribution unit can also provide audio content in download format. In addition, the distribution unit can also provide audio content in podcast format. This allows the audio content creation system according to the embodiment to allow visually impaired or bedridden people to enjoy video content such as movies and dramas. Some or all of the processing described above in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content.

[0030] The acquisition unit acquires auditory information from video content. For example, the acquisition unit can acquire auditory information such as dialogue, music, and sound effects from video content. Specifically, the acquisition unit can use a high-sensitivity microphone to clearly collect ambient sounds. This makes it possible to directly extract auditory information from the audio track of the video content. Furthermore, the acquisition unit can also convert the audio of video content into text data using speech recognition technology. For example, speech recognition technology utilizes a deep learning-based speech recognition model to convert audio data into text with high accuracy. Pre-processing is also performed to remove background noise and clarify the audio. In addition, the acquisition unit can use technology to simultaneously collect audio from multiple sound sources and separate each sound source. This makes it possible to individually acquire different types of auditory information, such as dialogue, music, and sound effects, and provide them to the analysis unit. By combining these technologies, the acquisition unit can acquire auditory information from video content with high accuracy and efficiency, improving the overall system performance.

[0031] The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. For example, the analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. Specifically, it uses facial recognition technology to analyze the facial expressions of characters and understand changes in emotions and the relationships between characters. It also uses scene analysis technology to analyze the scenery and understand the background and atmosphere of the scene. Furthermore, it uses object recognition technology to identify objects in the video and acquire detailed information about the scene. For example, it identifies objects held by characters or buildings in the background and analyzes the impact they have on the scene. By combining these technologies, the analysis unit analyzes the visual information of the video content in detail and generates basic data to provide to the language translation unit. Furthermore, the analysis unit can track the temporal changes in the video and understand the transitions between scenes and the progress of the story. In this way, the analysis unit can comprehensively analyze the visual information of the video content and improve the accuracy and reliability of the entire system.

[0032] The language processing unit translates the visual information analyzed by the analysis unit into language. For example, the language processing unit can convert visual information into text data using natural language processing techniques. Specifically, it can use text generation AI to convert visual information into natural language. In this process, algorithms for generating grammatically correct sentences can also be used. For instance, it can generate sentences that describe the characters' actions and expressions in detail based on the visual information, and explain the background and atmosphere of the scene. Furthermore, the language processing unit can also use techniques to generate semantically consistent sentences. This ensures that the text data based on the visual information accurately reflects the flow of the story and the relationships between the characters. By combining these techniques, the language processing unit generates foundational data to provide to the speech conversion unit, converting visual information into highly accurate and natural language. Furthermore, the language processing unit can evaluate the quality of the generated text data and make corrections or improvements as needed. This allows the language processing unit to accurately convert visual information into natural language and improve the overall system performance.

[0033] The speech conversion unit converts the visual information verbalized by the language conversion unit into speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. Specifically, it uses speech synthesis AI to generate natural-sounding speech. In this process, techniques for adjusting intonation and accent can also be used. For example, the tone and rhythm of the speech can be adjusted according to the emotions of the characters or the atmosphere of the scene to generate more realistic speech. Furthermore, the speech conversion unit can also use algorithms to improve the fluency of the speech. This makes the generated speech natural and easy to understand. By combining these technologies, the speech conversion unit converts the verbalized visual information into highly accurate and natural speech, generating basic data to provide to the data provider. Furthermore, the speech conversion unit can evaluate the quality of the generated speech data and make corrections or improvements as needed. This allows the speech conversion unit to accurately convert visual information into natural speech, improving the overall system performance.

[0034] The content provider unit provides audio content by combining the voice converted by the voice conversion unit with auditory information. The content provider unit can provide audio content, for example, through a streaming service. Specifically, it can distribute audio content through web applications or mobile applications. The content provider unit can also provide audio content in download format. Furthermore, the content provider unit can provide audio content in podcast format. This allows the audio content creation system according to the embodiment to allow visually impaired or bedridden people to enjoy video content such as movies and dramas. Some or all of the processing described above in the content provider unit may be performed using AI, for example, or without AI. For example, the content provider unit can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content. Specifically, the AI ​​model can recommend the most suitable audio content based on the user's preferences and past viewing history. Furthermore, the content provider unit can collect feedback from users and continuously improve the quality and method of content delivery. This allows the content provider unit to provide high-quality audio content to users and improve the overall performance of the system.

[0035] The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. For example, the analysis unit can analyze the facial expressions of characters using facial recognition technology. For example, the analysis unit can identify the smiles and angry expressions of characters. The analysis unit can also analyze the scenery using scene analysis technology. For example, the analysis unit can identify scenery such as parks and buildings in the video. Furthermore, the analysis unit can identify objects in the video using object recognition technology. For example, the analysis unit can identify objects such as cars and furniture in the video. This enables detailed analysis of visual information. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input video data into the generation AI and have the generation AI perform the analysis of the facial expressions of characters and the scenery.

[0036] The language conversion unit can convert visual information analyzed by the analysis unit into natural language. For example, the language conversion unit can convert visual information into text data using natural language processing techniques. For example, the language conversion unit can convert the facial expressions of characters and scenes into grammatically correct sentences. The language conversion unit can also convert visual information into natural language using text generation AI. For example, the language conversion unit can convert the facial expressions of characters into sentences such as "She looked down shyly." Furthermore, the language conversion unit can also use techniques to generate semantically consistent sentences. For example, the language conversion unit can convert a scene into sentences such as "In a small park in a big city." This allows visual information to be expressed in natural language. Some or all of the above processing in the language conversion unit is performed using generation AI. For example, the language conversion unit can input visual information analyzed by the analysis unit into generation AI and have generation AI perform the conversion into natural language.

[0037] The speech conversion unit can convert visual information verbalized by the language conversion unit into natural speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. For example, the speech conversion unit can provide verbalized visual information in natural speech. Furthermore, the speech conversion unit can generate natural speech using speech synthesis AI. For example, the speech conversion unit can provide visual information such as "She looked down shyly" in natural speech. In addition, the speech conversion unit can use techniques to adjust intonation and accent. For example, the speech conversion unit can use algorithms to improve speech fluency. This allows visual information to be provided in natural speech. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input visual information verbalized by the language conversion unit into a generation AI, and have the generation AI perform the conversion into natural speech.

[0038] The service provider can provide audio content by combining the voice converted by the voice conversion unit with auditory information. For example, the service provider can combine the voice converted by the voice conversion unit with auditory information such as dialogue, music, and sound effects from video content. For example, the service provider can create audio content by combining the audio of visual information converted by the voice conversion unit with dialogue from video content. The service provider can also combine the audio of visual information converted by the voice conversion unit with music from video content. Furthermore, the service provider can combine the audio of visual information converted by the voice conversion unit with sound effects from video content. This makes it possible to provide audio content that combines visual and auditory information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content.

[0039] The provider can provide audio content with commentary through streaming services. For example, the provider can distribute audio content with commentary through web applications or mobile applications. For instance, the provider can provide audio content with commentary for movies and dramas through streaming services. The provider can also provide audio content with commentary in downloadable format. For example, the provider can allow users to download audio content with commentary for offline viewing. Furthermore, the provider can provide audio content with commentary in podcast format. For example, the provider can distribute regularly updated audio content with commentary as a podcast. This allows the provider to deliver audio content with commentary through streaming services. Some or all of the above processes in the provider may be performed using AI or not. For example, the provider can provide audio content using an AI model that generates audio content with commentary.

[0040] The acquisition unit can filter the auditory information to be acquired according to the type of video content. For example, in the case of a drama, the acquisition unit can acquire auditory information mainly from dialogue. For example, the acquisition unit can prioritize the acquisition of dialogue in a drama. Also, in the case of an action movie, the acquisition unit can acquire auditory information mainly from sound effects. For example, the acquisition unit can prioritize the acquisition of sound effects in action scenes. Furthermore, in the case of a documentary, the acquisition unit can acquire auditory information mainly from narration. For example, the acquisition unit can prioritize the acquisition of narration in a documentary. This makes it possible to filter auditory information according to the type of video content. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the type of video content into the AI ​​and have the AI ​​perform the filtering of the auditory information to be acquired.

[0041] The acquisition unit can perform noise reduction when acquiring auditory information, thereby obtaining clear audio data. For example, the acquisition unit can remove background noise and clearly acquire dialogue. For example, the acquisition unit can filter background noise in video content and clearly acquire dialogue. The acquisition unit can also remove wind noise and clearly acquire sound effects. For example, the acquisition unit can filter wind noise and clearly acquire sound effects. Furthermore, the acquisition unit can remove background noise and clearly acquire music. For example, the acquisition unit can filter background noise and clearly acquire music. This allows for the acquisition of clear audio data through noise reduction. Some or all of the above processing in the acquisition unit may be performed using AI, or it may not be performed using AI. For example, the acquisition unit can have AI perform the noise reduction filtering.

[0042] The acquisition unit can prioritize the acquisition of highly relevant information based on the user's viewing history when acquiring auditory information. For example, if the acquisition unit is watching a sequel to a drama series the user has previously watched, it can prioritize the acquisition of lines spoken by the main characters. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant lines. Similarly, if the acquisition unit is watching a sequel to an action movie the user has previously watched, it can prioritize the acquisition of sound effects from action scenes. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant sound effects. Furthermore, if the acquisition unit is watching a sequel to a documentary the user has previously watched, it can prioritize the acquisition of narration. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant narration. This allows for the priority acquisition of highly relevant information based on the user's viewing history. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's viewing history into AI and have AI perform the acquisition of highly relevant information.

[0043] The acquisition unit can acquire auditory information in conjunction with subtitle information from video content. For example, the acquisition unit can analyze subtitle information from video content and acquire auditory information of dialogue. For example, the acquisition unit can clearly acquire dialogue based on subtitle information. The acquisition unit can also analyze subtitle information from video content and acquire auditory information of sound effects. For example, the acquisition unit can clearly acquire sound effects based on subtitle information. Furthermore, the acquisition unit can analyze subtitle information from video content and acquire auditory information of music. For example, the acquisition unit can clearly acquire music based on subtitle information. This makes it possible to acquire more accurate auditory information by using subtitle information in conjunction. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input subtitle information into AI and have AI perform the acquisition of auditory information.

[0044] The analysis unit can optimize its analysis algorithm according to the genre of the video content. For example, in the case of a drama, the analysis unit may prioritize the analysis of the characters' facial expressions. For instance, the analysis unit can analyze the characters' facial expressions in detail within a drama scene. Similarly, in the case of an action movie, the analysis unit may prioritize motion analysis. For example, the analysis unit can analyze the characters' movements in detail within an action scene. Furthermore, in the case of a documentary, the analysis unit may prioritize the analysis of scenery and objects. For example, the analysis unit can analyze scenery and objects in detail within a documentary scene. This enables analysis tailored to the genre of the video content. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input the genre of the video content into the generative AI and have the generative AI optimize the analysis algorithm.

[0045] The analysis unit can adjust the analysis accuracy according to the frame rate of the video when analyzing visual information. For example, the analysis unit can improve the accuracy of motion analysis in high-frame-rate video. For example, the analysis unit can improve the accuracy of motion analysis in high-frame-rate action scenes. The analysis unit can also improve the accuracy of still image analysis in low-frame-rate video. For example, the analysis unit can improve the accuracy of still image analysis in low-frame-rate landscape scenes. Furthermore, the analysis unit can dynamically adjust the analysis accuracy in video with fluctuating frame rates. For example, the analysis unit can adjust the analysis accuracy in real time according to fluctuations in the frame rate. This makes it possible to adjust the analysis accuracy according to the frame rate. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the video's frame rate to the generation AI and have the generation AI perform the adjustment of the analysis accuracy.

[0046] The analysis unit can improve the accuracy of its analysis by referring to the metadata of the video content when analyzing visual information. For example, the analysis unit can identify the names of characters based on the metadata of the video content. For example, the analysis unit can identify the names of characters by referring to the metadata and improve the accuracy of its analysis. The analysis unit can also identify the location of a scene based on the metadata of the video content. For example, the analysis unit can identify the location of a scene by referring to the metadata and improve the accuracy of its analysis. Furthermore, the analysis unit can also identify the time of day based on the metadata of the video content. For example, the analysis unit can identify the time of day of a scene by referring to the metadata and improve the accuracy of its analysis. In this way, the accuracy of the analysis is improved by referring to the metadata. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the metadata of the video content into the generation AI and have the generation AI perform the improvement of the analysis accuracy.

[0047] The analysis unit can apply different analysis methods to each scene of the video content when analyzing visual information. For example, in action scenes, the analysis unit can prioritize motion analysis. For instance, it can analyze the movements of characters in detail in action scenes. The analysis unit can also prioritize facial expression analysis in dialogue scenes. For instance, it can analyze the facial expressions of characters in detail in dialogue scenes. Furthermore, the analysis unit can also prioritize object analysis in landscape scenes. For instance, it can analyze landscapes and objects in detail in landscape scenes. By applying the appropriate analysis method to each scene, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input the characteristics of each scene into the generative AI and have the generative AI execute the application of the appropriate analysis method.

[0048] The verbalization unit can adjust the level of detail in verbalization based on the importance of the visual information. For example, the verbalization unit can perform detailed verbalization in important scenes. For example, the verbalization unit can verbalize visual information in detail in important scenes. The verbalization unit can also perform concise verbalization in scenes of low importance. For example, the verbalization unit can verbalize visual information concisely in scenes of low importance. Furthermore, the verbalization unit can verbalize with an appropriate level of detail in scenes of moderate importance. For example, the verbalization unit can verbalize visual information with an appropriate level of detail in scenes of moderate importance. This makes it possible to adjust the level of detail in verbalization according to the importance of the visual information. Some or all of the above processing in the verbalization unit is performed using a generative AI. For example, the verbalization unit can input the importance of the visual information into the generative AI and have the generative AI perform the adjustment of the level of detail in verbalization.

[0049] The language processing unit can apply different language processing algorithms depending on the context of the video content during the language processing process. For example, in dramas, the language processing unit can perform language processing that emphasizes emotional expression. For instance, it can perform language processing that richly expresses the emotions of the characters in a drama scene. Furthermore, in action movies, the language processing unit can perform language processing that emphasizes the expression of actions. For instance, it can perform language processing that describes the actions of the characters in an action scene in detail. In addition, in documentaries, the language processing unit can perform language processing that emphasizes the expression of facts. For instance, it can perform language processing that accurately expresses the facts in a documentary scene. This enables language processing that is appropriate to the context of the video content. Some or all of the above processing in the language processing unit is performed using a generative AI. For example, the language processing unit can input the context of the video content into the generative AI and have the generative AI apply an appropriate language processing algorithm.

[0050] The language processing unit can determine the priority of language processing based on the frequency of occurrence of visual information. For example, the language processing unit can prioritize the language processing of frequently occurring visual information. The language processing unit can also postpone the processing of less frequently occurring visual information. Furthermore, the language processing unit can adjust the order of language processing according to the frequency of occurrence. For example, the language processing unit can adjust the order of language processing of visual information according to the frequency of occurrence. This makes it possible to determine the priority of language processing according to the frequency of occurrence of visual information. Some or all of the above processing in the language processing unit is performed using a generative AI. For example, the language processing unit can input the frequency of occurrence of visual information to the generative AI and have the generative AI perform the determination of the priority of language processing.

[0051] The verbalization unit can adjust the order of verbalization based on the relevance of the visual information. For example, the verbalization unit can prioritize verbalizing important visual information. The verbalization unit can also postpone the verbalization of less relevant visual information. Furthermore, the verbalization unit can adjust the order of verbalization according to relevance. For example, the verbalization unit can adjust the order of verbalization of visual information according to relevance. This makes it possible to adjust the order of verbalization according to the relevance of the visual information. Some or all of the above processing in the verbalization unit is performed using a generative AI. For example, the verbalization unit can input the relevance of the visual information into the generative AI and have the generative AI perform the adjustment of the verbalization order.

[0052] The speech conversion unit can adjust the volume of the speech based on the importance of the verbalized information during speech conversion. For example, the speech conversion unit can emphasize important information during speech conversion. For example, the speech conversion unit can emphasize important visual information during speech conversion. The speech conversion unit can also convert less important information to a lower volume. For example, the speech conversion unit can convert less important visual information to a lower volume. Furthermore, the speech conversion unit can convert information of moderate importance to an appropriate volume. For example, the speech conversion unit can convert visual information of moderate importance to an appropriate volume. This makes it possible to adjust the volume of the speech according to the importance of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the importance of the verbalized information into the generation AI and have the generation AI perform the adjustment of the volume of the speech.

[0053] The audio conversion unit can apply different audio conversion algorithms depending on the genre of the video content during audio conversion. For example, in dramas, the audio conversion unit can perform audio conversion that emphasizes emotional expression. For instance, it can perform audio conversion that richly expresses the emotions of the characters in a drama scene. Furthermore, in action movies, the audio conversion unit can perform audio conversion that emphasizes the expression of actions. For example, it can perform audio conversion that accurately expresses the actions of the characters in an action scene. Additionally, in documentaries, the audio conversion unit can perform audio conversion that emphasizes the expression of facts. For example, it can perform audio conversion that accurately expresses the facts in a documentary scene. This enables audio conversion tailored to the genre of the video content. Some or all of the above processing in the audio conversion unit is performed using a generative AI. For example, the audio conversion unit can input the genre of the video content into the generative AI and have the generative AI apply an appropriate audio conversion algorithm.

[0054] The speech conversion unit can determine the priority of speech based on the frequency of occurrence of the verbalized information during speech conversion. For example, the speech conversion unit can prioritize the conversion of frequently occurring information. For example, the speech conversion unit can prioritize the conversion of frequently occurring visual information. The speech conversion unit can also postpone the conversion of less frequently occurring information. For example, the speech conversion unit can postpone the conversion of less frequently occurring visual information. Furthermore, the speech conversion unit can adjust the order of speech conversion according to the frequency of occurrence. For example, the speech conversion unit can adjust the order of speech conversion of visual information according to its frequency of occurrence. This makes it possible to determine the priority of speech based on the frequency of occurrence of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the frequency of occurrence of the verbalized information into the generation AI and have the generation AI perform the determination of speech priority.

[0055] The speech conversion unit can adjust the order of speech based on the relevance of the verbalized information during speech conversion. For example, the speech conversion unit can prioritize the conversion of important information. For example, the speech conversion unit can prioritize the conversion of important visual information. The speech conversion unit can also postpone the conversion of less relevant information. For example, the speech conversion unit can postpone the conversion of less relevant visual information. Furthermore, the speech conversion unit can adjust the order of speech conversion according to relevance. For example, the speech conversion unit can adjust the order of speech conversion of visual information according to relevance. This makes it possible to adjust the order of speech according to the relevance of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the relevance of the verbalized information into the generation AI and have the generation AI perform the adjustment of the order of speech.

[0056] The delivery unit can select the optimal delivery method when delivering audio content by referring to the user's past viewing history. For example, the delivery unit can select the optimal delivery method based on the user's past viewing trends. For example, the delivery unit can analyze the user's viewing history and select the optimal delivery method based on the user's past viewing trends. The delivery unit can also select a delivery method that matches the user's preferred genre based on their past viewing history. For example, the delivery unit can analyze the user's viewing history and select a delivery method that matches their preferred genre. Furthermore, the delivery unit can analyze the user's past viewing history and select the most efficient delivery method. For example, the delivery unit can analyze the user's viewing history and select the most efficient delivery method. This makes it possible to select the optimal delivery method based on the user's past viewing history. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's viewing history into AI and have the AI ​​select the optimal delivery method.

[0057] The delivery unit can customize the delivery method when providing audio content according to the genre of the video content. For example, in the case of a drama, the delivery unit can select a delivery method that emphasizes emotional expression. For example, the delivery unit can select a delivery method that emphasizes emotional expression in drama scenes. Also, in the case of an action movie, the delivery unit can select a delivery method that emphasizes action expression. For example, the delivery unit can select a delivery method that emphasizes action expression in action scenes. Furthermore, in the case of a documentary, the delivery unit can select a delivery method that emphasizes factual expression. For example, the delivery unit can select a delivery method that emphasizes factual expression in documentary scenes. This makes it possible to customize the delivery method according to the genre of the video content. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the genre of the video content into the AI ​​and have the AI ​​perform the customization of the delivery method.

[0058] The delivery unit can select the optimal delivery method based on the user's device information when delivering audio content. For example, if the user is using a smartphone, the delivery unit can select a delivery method that matches the screen size. For example, the delivery unit can deliver audio content optimized for the smartphone screen size. Also, if the user is using a tablet, the delivery unit can select a delivery method optimized for the larger screen. For example, the delivery unit can deliver audio content optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the delivery unit can select a concise and highly visible delivery method. For example, the delivery unit can deliver audio content optimized for the small screen of a smartwatch. This makes it possible to select the optimal delivery method based on the user's device information. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's device information into AI and have the AI ​​select the optimal delivery method.

[0059] The delivery unit can adjust the delivery method based on the user's listening environment when delivering audio content. For example, if the user is in a quiet environment, the delivery unit can select a detailed delivery method. For example, the delivery unit can deliver detailed audio content in a quiet environment. The delivery unit can also select a concise delivery method if the user is in a noisy environment. For example, the delivery unit can deliver concise audio content in a noisy environment. Furthermore, if the user is on the move, the delivery unit can adjust the delivery method in real time. For example, the delivery unit can deliver the optimal audio content to a user on the move in real time. This makes it possible to adjust the delivery method according to the user's listening environment. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's listening environment into AI and have the AI ​​perform the adjustment of the delivery method.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The audio content creation system can also include a customized audio filtering function based on user preferences. For example, if a user prefers a particular music genre, music of that genre can be filtered to prioritize it. Similarly, if a user prefers a specific voice tone or accent, filtering can be applied to emphasize that tone or accent. Furthermore, if a user prefers a specific sound effect, filtering can be applied to emphasize that sound effect. This allows for the provision of customized audio content tailored to the user's preferences.

[0062] The analysis unit can apply different analysis algorithms to each scene of the video content. For example, it can prioritize motion analysis in action scenes and facial expression analysis in dialogue scenes. It can also prioritize object analysis in landscape scenes. Furthermore, the analysis unit can switch analysis algorithms in real time according to changes in the scene. This enables optimal analysis for each scene.

[0063] The acquisition unit can determine the priority of auditory information to acquire by referring to the metadata of the video content. For example, it can prioritize the acquisition of important dialogue and sound effects based on the metadata. It can also prioritize the acquisition of music from a specific scene based on the metadata. Furthermore, it can prioritize the acquisition of dialogue from a specific character based on the metadata. This enables efficient acquisition of auditory information by utilizing metadata.

[0064] The analysis unit can optimize its analysis algorithm according to the genre of video content. For example, it can prioritize facial expression analysis for dramas and motion analysis for action movies. It can also prioritize the analysis of scenery and objects for documentaries. Furthermore, the analysis unit can improve analysis accuracy by applying different analysis algorithms for each genre. This enables optimal analysis tailored to each genre.

[0065] The verbalization unit can determine the priority of verbalization based on the frequency of occurrence of visual information. For example, it can prioritize verbalizing frequently occurring visual information. It can also postpone the verbalization of less frequently occurring visual information. Furthermore, it can adjust the order of verbalization according to the frequency of occurrence. This enables efficient verbalization in accordance with the frequency of occurrence of visual information.

[0066] The speech conversion unit can adjust the volume of the speech based on the importance of the information being spoken. For example, important information can be emphasized during speech conversion. Less important information can be converted more subtly. Furthermore, information of moderate importance can be converted with an appropriate volume. This makes it possible to adjust the volume of the speech according to the importance of the information being spoken.

[0067] The delivery unit can select the optimal delivery method based on the user's device information. For example, if the user is using a smartphone, it can select a delivery method that matches the screen size. If the user is using a tablet, it can select a delivery method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can select a concise and highly visible delivery method. This makes it possible to select the optimal delivery method based on the user's device information.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The acquisition unit acquires auditory information from the video content. The acquisition unit can acquire auditory information such as dialogue, music, and sound effects from the video content. The acquisition unit can collect audio using a microphone or extract auditory information directly from the audio track of the video content. It can also convert the audio of the video content into text data using speech recognition technology. Step 2: The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. The analysis unit can analyze the facial expressions of characters using face recognition technology and analyze the scenery using scene analysis technology. Furthermore, it can also identify objects in the video using object recognition technology. Step 3: The language processing unit translates the visual information analyzed by the analysis unit into language. The language processing unit can convert the visual information into text data using natural language processing techniques. The language processing unit can use text generation AI to convert the visual information into natural language and can employ algorithms to generate grammatically correct sentences. Furthermore, it can also employ techniques to generate semantically consistent sentences. Step 4: The speech conversion unit converts the visual information verbalized by the language conversion unit into speech. The speech conversion unit can convert text data into speech data using speech synthesis technology. The speech conversion unit can use speech synthesis AI to generate natural-sounding speech and can employ techniques to adjust intonation and accent. Furthermore, it can also use algorithms to improve speech fluency. Step 5: The delivery unit combines the audio converted by the speech conversion unit with auditory information to provide audio content. The delivery unit can provide audio content through streaming services. The delivery unit can distribute audio content through web applications and mobile applications. It can also provide audio content in download format. Furthermore, it can provide audio content in podcast format.

[0070] (Example of form 2) An audio content creation system according to an embodiment of the present invention is a system that acquires auditory information from video content, and a generating AI analyzes the visual information contained in the video, verbalizes it, and converts it into speech. This audio content creation system is intended for visually impaired or bedridden people to enjoy video content such as movies and dramas. The audio content creation system acquires auditory information such as dialogue, music, and sound effects from the video content. Next, the generating AI analyzes the visual information contained in the video and verbalizes the facial expressions of the characters and the scenery. For example, it verbalizes visual information such as "She looked down shyly" or "In a small park in the middle of a big city." Next, it converts the verbalized visual information into speech. At this time, the generating AI can read the visual information aloud in a natural voice. For example, it provides visual information such as "She looked down shyly" as speech. Finally, it combines auditory information such as dialogue, music, and sound effects with the verbalized visual information to create audio content. For example, the audio content creation system is intended for visually impaired or bedridden people to enjoy video content such as movies and dramas. For example, it can provide audio content with commentary through a streaming service. This makes it possible for everyone to enjoy video content. This means that audio content creation systems can allow visually impaired or bedridden people to enjoy video content such as movies and dramas.

[0071] The audio content creation system according to this embodiment comprises an acquisition unit, an analysis unit, a language conversion unit, a speech conversion unit, and a provision unit. The acquisition unit acquires auditory information from video content. The acquisition unit can acquire auditory information such as dialogue, music, and sound effects from video content. The acquisition unit collects audio using a microphone, for example. The acquisition unit can also directly extract auditory information from the audio track of video content. Furthermore, the acquisition unit can convert the audio of video content into text data using speech recognition technology. The analysis unit analyzes visual information contained in the video based on the auditory information acquired by the acquisition unit. The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video, for example. The analysis unit analyzes the facial expressions of characters using face recognition technology, for example. The analysis unit can also analyze the scenery using scene analysis technology. Furthermore, the analysis unit can identify objects in the video using object recognition technology. The language conversion unit translates the visual information analyzed by the analysis unit into language. The language processing unit can, for example, convert visual information into text data using natural language processing technology. The language processing unit can convert visual information into natural language using, for example, text generation AI. The language processing unit can also use algorithms to generate grammatically correct sentences. Furthermore, the language processing unit can use techniques to generate semantically consistent sentences. The speech conversion unit converts the visual information languaged by the language processing unit into speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. The speech conversion unit can, for example, generate natural speech using speech synthesis AI. Furthermore, the speech conversion unit can use techniques to adjust intonation and accent. Furthermore, the speech conversion unit can use algorithms to improve speech fluency. The delivery unit combines the speech converted by the speech conversion unit with auditory information to provide audio content. The delivery unit can, for example, provide audio content through streaming services. The delivery unit can, for example, distribute audio content through web applications or mobile applications.Furthermore, the distribution unit can also provide audio content in download format. In addition, the distribution unit can also provide audio content in podcast format. This allows the audio content creation system according to the embodiment to allow visually impaired or bedridden people to enjoy video content such as movies and dramas. Some or all of the processing described above in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content.

[0072] The acquisition unit acquires auditory information from video content. For example, the acquisition unit can acquire auditory information such as dialogue, music, and sound effects from video content. Specifically, the acquisition unit can use a high-sensitivity microphone to clearly collect ambient sounds. This makes it possible to directly extract auditory information from the audio track of the video content. Furthermore, the acquisition unit can also convert the audio of video content into text data using speech recognition technology. For example, speech recognition technology utilizes a deep learning-based speech recognition model to convert audio data into text with high accuracy. Pre-processing is also performed to remove background noise and clarify the audio. In addition, the acquisition unit can use technology to simultaneously collect audio from multiple sound sources and separate each sound source. This makes it possible to individually acquire different types of auditory information, such as dialogue, music, and sound effects, and provide them to the analysis unit. By combining these technologies, the acquisition unit can acquire auditory information from video content with high accuracy and efficiency, improving the overall system performance.

[0073] The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. For example, the analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. Specifically, it uses facial recognition technology to analyze the facial expressions of characters and understand changes in emotions and the relationships between characters. It also uses scene analysis technology to analyze the scenery and understand the background and atmosphere of the scene. Furthermore, it uses object recognition technology to identify objects in the video and acquire detailed information about the scene. For example, it identifies objects held by characters or buildings in the background and analyzes the impact they have on the scene. By combining these technologies, the analysis unit analyzes the visual information of the video content in detail and generates basic data to provide to the language translation unit. Furthermore, the analysis unit can track the temporal changes in the video and understand the transitions between scenes and the progress of the story. In this way, the analysis unit can comprehensively analyze the visual information of the video content and improve the accuracy and reliability of the entire system.

[0074] The language processing unit translates the visual information analyzed by the analysis unit into language. For example, the language processing unit can convert visual information into text data using natural language processing techniques. Specifically, it can use text generation AI to convert visual information into natural language. In this process, algorithms for generating grammatically correct sentences can also be used. For instance, it can generate sentences that describe the characters' actions and expressions in detail based on the visual information, and explain the background and atmosphere of the scene. Furthermore, the language processing unit can also use techniques to generate semantically consistent sentences. This ensures that the text data based on the visual information accurately reflects the flow of the story and the relationships between the characters. By combining these techniques, the language processing unit generates foundational data to provide to the speech conversion unit, converting visual information into highly accurate and natural language. Furthermore, the language processing unit can evaluate the quality of the generated text data and make corrections or improvements as needed. This allows the language processing unit to accurately convert visual information into natural language and improve the overall system performance.

[0075] The speech conversion unit converts the visual information verbalized by the language conversion unit into speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. Specifically, it uses speech synthesis AI to generate natural-sounding speech. In this process, techniques for adjusting intonation and accent can also be used. For example, the tone and rhythm of the speech can be adjusted according to the emotions of the characters or the atmosphere of the scene to generate more realistic speech. Furthermore, the speech conversion unit can also use algorithms to improve the fluency of the speech. This makes the generated speech natural and easy to understand. By combining these technologies, the speech conversion unit converts the verbalized visual information into highly accurate and natural speech, generating basic data to provide to the data provider. Furthermore, the speech conversion unit can evaluate the quality of the generated speech data and make corrections or improvements as needed. This allows the speech conversion unit to accurately convert visual information into natural speech, improving the overall system performance.

[0076] The content provider unit provides audio content by combining the voice converted by the voice conversion unit with auditory information. The content provider unit can provide audio content, for example, through a streaming service. Specifically, it can distribute audio content through web applications or mobile applications. The content provider unit can also provide audio content in download format. Furthermore, the content provider unit can provide audio content in podcast format. This allows the audio content creation system according to the embodiment to allow visually impaired or bedridden people to enjoy video content such as movies and dramas. Some or all of the processing described above in the content provider unit may be performed using AI, for example, or without AI. For example, the content provider unit can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content. Specifically, the AI ​​model can recommend the most suitable audio content based on the user's preferences and past viewing history. Furthermore, the content provider unit can collect feedback from users and continuously improve the quality and method of content delivery. This allows the content provider unit to provide high-quality audio content to users and improve the overall performance of the system.

[0077] The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. For example, the analysis unit can analyze the facial expressions of characters using facial recognition technology. For example, the analysis unit can identify the smiles and angry expressions of characters. The analysis unit can also analyze the scenery using scene analysis technology. For example, the analysis unit can identify scenery such as parks and buildings in the video. Furthermore, the analysis unit can identify objects in the video using object recognition technology. For example, the analysis unit can identify objects such as cars and furniture in the video. This enables detailed analysis of visual information. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input video data into the generation AI and have the generation AI perform the analysis of the facial expressions of characters and the scenery.

[0078] The language conversion unit can convert visual information analyzed by the analysis unit into natural language. For example, the language conversion unit can convert visual information into text data using natural language processing techniques. For example, the language conversion unit can convert the facial expressions of characters and scenes into grammatically correct sentences. The language conversion unit can also convert visual information into natural language using text generation AI. For example, the language conversion unit can convert the facial expressions of characters into sentences such as "She looked down shyly." Furthermore, the language conversion unit can also use techniques to generate semantically consistent sentences. For example, the language conversion unit can convert a scene into sentences such as "In a small park in a big city." This allows visual information to be expressed in natural language. Some or all of the above processing in the language conversion unit is performed using generation AI. For example, the language conversion unit can input visual information analyzed by the analysis unit into generation AI and have generation AI perform the conversion into natural language.

[0079] The speech conversion unit can convert visual information verbalized by the language conversion unit into natural speech. The speech conversion unit can, for example, convert text data into speech data using speech synthesis technology. For example, the speech conversion unit can provide verbalized visual information in natural speech. Furthermore, the speech conversion unit can generate natural speech using speech synthesis AI. For example, the speech conversion unit can provide visual information such as "She looked down shyly" in natural speech. In addition, the speech conversion unit can use techniques to adjust intonation and accent. For example, the speech conversion unit can use algorithms to improve speech fluency. This allows visual information to be provided in natural speech. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input visual information verbalized by the language conversion unit into a generation AI, and have the generation AI perform the conversion into natural speech.

[0080] The service provider can provide audio content by combining the voice converted by the voice conversion unit with auditory information. For example, the service provider can combine the voice converted by the voice conversion unit with auditory information such as dialogue, music, and sound effects from video content. For example, the service provider can create audio content by combining the audio of visual information converted by the voice conversion unit with dialogue from video content. The service provider can also combine the audio of visual information converted by the voice conversion unit with music from video content. Furthermore, the service provider can combine the audio of visual information converted by the voice conversion unit with sound effects from video content. This makes it possible to provide audio content that combines visual and auditory information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can provide audio content using an AI model that takes the voice converted by the voice conversion unit and auditory information as input and outputs audio content.

[0081] The provider can provide audio content with commentary through streaming services. For example, the provider can distribute audio content with commentary through web applications or mobile applications. For instance, the provider can provide audio content with commentary for movies and dramas through streaming services. The provider can also provide audio content with commentary in downloadable format. For example, the provider can allow users to download audio content with commentary for offline viewing. Furthermore, the provider can provide audio content with commentary in podcast format. For example, the provider can distribute regularly updated audio content with commentary as a podcast. This allows the provider to deliver audio content with commentary through streaming services. Some or all of the above processes in the provider may be performed using AI or not. For example, the provider can provide audio content using an AI model that generates audio content with commentary.

[0082] The acquisition unit can estimate the user's emotions and adjust the timing of auditory information acquisition based on the estimated user emotions. For example, the acquisition unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the acquisition unit can calculate an emotion score based on changes in facial expressions. The acquisition unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the acquisition unit can analyze the tone and speed of the voice and calculate an emotion score. The acquisition unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the acquisition unit can calculate an emotion score based on fluctuations in heart rate. This allows the timing of auditory information acquisition to be adjusted 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 acquisition unit may be performed using AI or not. For example, the acquisition unit can input image data of the user captured by the camera into a generating AI, and have the generating AI perform the estimation of the user's emotions.

[0083] The acquisition unit can filter the auditory information to be acquired according to the type of video content. For example, in the case of a drama, the acquisition unit can acquire auditory information mainly from dialogue. For example, the acquisition unit can prioritize the acquisition of dialogue in a drama. Also, in the case of an action movie, the acquisition unit can acquire auditory information mainly from sound effects. For example, the acquisition unit can prioritize the acquisition of sound effects in action scenes. Furthermore, in the case of a documentary, the acquisition unit can acquire auditory information mainly from narration. For example, the acquisition unit can prioritize the acquisition of narration in a documentary. This makes it possible to filter auditory information according to the type of video content. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the type of video content into the AI ​​and have the AI ​​perform the filtering of the auditory information to be acquired.

[0084] The acquisition unit can perform noise reduction when acquiring auditory information, thereby obtaining clear audio data. For example, the acquisition unit can remove background noise and clearly acquire dialogue. For example, the acquisition unit can filter background noise in video content and clearly acquire dialogue. The acquisition unit can also remove wind noise and clearly acquire sound effects. For example, the acquisition unit can filter wind noise and clearly acquire sound effects. Furthermore, the acquisition unit can remove background noise and clearly acquire music. For example, the acquisition unit can filter background noise and clearly acquire music. This allows for the acquisition of clear audio data through noise reduction. Some or all of the above processing in the acquisition unit may be performed using AI, or it may not be performed using AI. For example, the acquisition unit can have AI perform the noise reduction filtering.

[0085] The acquisition unit can estimate the user's emotions and determine the priority of auditory information to acquire based on the estimated user emotions. For example, the acquisition unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the acquisition unit can calculate an emotion score based on changes in facial expressions. The acquisition unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the acquisition unit can analyze the tone and speed of the voice and calculate an emotion score. The acquisition unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the acquisition unit can calculate an emotion score based on fluctuations in heart rate. This allows the system to determine the priority of auditory information 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-described processes in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input image data of the user captured by the camera into a generating AI, and have the generating AI perform the estimation of the user's emotions.

[0086] The acquisition unit can prioritize the acquisition of highly relevant information based on the user's viewing history when acquiring auditory information. For example, if the acquisition unit is watching a sequel to a drama series the user has previously watched, it can prioritize the acquisition of lines spoken by the main characters. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant lines. Similarly, if the acquisition unit is watching a sequel to an action movie the user has previously watched, it can prioritize the acquisition of sound effects from action scenes. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant sound effects. Furthermore, if the acquisition unit is watching a sequel to a documentary the user has previously watched, it can prioritize the acquisition of narration. For example, the acquisition unit can analyze the user's viewing history and prioritize the acquisition of highly relevant narration. This allows for the priority acquisition of highly relevant information based on the user's viewing history. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's viewing history into AI and have AI perform the acquisition of highly relevant information.

[0087] The acquisition unit can acquire auditory information in conjunction with subtitle information from video content. For example, the acquisition unit can analyze subtitle information from video content and acquire auditory information of dialogue. For example, the acquisition unit can clearly acquire dialogue based on subtitle information. The acquisition unit can also analyze subtitle information from video content and acquire auditory information of sound effects. For example, the acquisition unit can clearly acquire sound effects based on subtitle information. Furthermore, the acquisition unit can analyze subtitle information from video content and acquire auditory information of music. For example, the acquisition unit can clearly acquire music based on subtitle information. This makes it possible to acquire more accurate auditory information by using subtitle information in conjunction. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input subtitle information into AI and have AI perform the acquisition of auditory information.

[0088] The analysis unit can estimate the user's emotions and adjust the method of analyzing visual information based on the estimated user emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the analysis unit can calculate an emotion score based on changes in facial expressions. The analysis unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the voice and calculate an emotion score. The analysis unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the analysis unit can calculate an emotion score based on fluctuations in heart rate. This allows the method of analyzing visual information to be adjusted 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit are performed using generative AI. For example, the analysis unit can input user emotion data into the generating AI and have the generating AI adjust the method of analyzing visual information.

[0089] The analysis unit can optimize its analysis algorithm according to the genre of the video content. For example, in the case of a drama, the analysis unit may prioritize the analysis of the characters' facial expressions. For instance, the analysis unit can analyze the characters' facial expressions in detail within a drama scene. Similarly, in the case of an action movie, the analysis unit may prioritize motion analysis. For example, the analysis unit can analyze the characters' movements in detail within an action scene. Furthermore, in the case of a documentary, the analysis unit may prioritize the analysis of scenery and objects. For example, the analysis unit can analyze scenery and objects in detail within a documentary scene. This enables analysis tailored to the genre of the video content. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input the genre of the video content into the generative AI and have the generative AI optimize the analysis algorithm.

[0090] The analysis unit can adjust the analysis accuracy according to the frame rate of the video when analyzing visual information. For example, the analysis unit can improve the accuracy of motion analysis in high-frame-rate video. For example, the analysis unit can improve the accuracy of motion analysis in high-frame-rate action scenes. The analysis unit can also improve the accuracy of still image analysis in low-frame-rate video. For example, the analysis unit can improve the accuracy of still image analysis in low-frame-rate landscape scenes. Furthermore, the analysis unit can dynamically adjust the analysis accuracy in video with fluctuating frame rates. For example, the analysis unit can adjust the analysis accuracy in real time according to fluctuations in the frame rate. This makes it possible to adjust the analysis accuracy according to the frame rate. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the video's frame rate to the generation AI and have the generation AI perform the adjustment of the analysis accuracy.

[0091] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the analysis unit can calculate an emotion score based on changes in facial expressions. The analysis unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the voice and calculate an emotion score. The analysis unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the analysis unit can calculate an emotion score based on fluctuations in heart rate. This allows the display method of the analysis results to be adjusted 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-described processes in the analysis unit are performed using generative AI. For example, the analysis unit can input user emotion data into the generating AI and have the generating AI adjust how the analysis results are displayed.

[0092] The analysis unit can improve the accuracy of its analysis by referring to the metadata of the video content when analyzing visual information. For example, the analysis unit can identify the names of characters based on the metadata of the video content. For example, the analysis unit can identify the names of characters by referring to the metadata and improve the accuracy of its analysis. The analysis unit can also identify the location of a scene based on the metadata of the video content. For example, the analysis unit can identify the location of a scene by referring to the metadata and improve the accuracy of its analysis. Furthermore, the analysis unit can also identify the time of day based on the metadata of the video content. For example, the analysis unit can identify the time of day of a scene by referring to the metadata and improve the accuracy of its analysis. In this way, the accuracy of the analysis is improved by referring to the metadata. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input the metadata of the video content into the generation AI and have the generation AI perform the improvement of the analysis accuracy.

[0093] The analysis unit can apply different analysis methods to each scene of the video content when analyzing visual information. For example, in action scenes, the analysis unit can prioritize motion analysis. For instance, it can analyze the movements of characters in detail in action scenes. The analysis unit can also prioritize facial expression analysis in dialogue scenes. For instance, it can analyze the facial expressions of characters in detail in dialogue scenes. Furthermore, the analysis unit can also prioritize object analysis in landscape scenes. For instance, it can analyze landscapes and objects in detail in landscape scenes. By applying the appropriate analysis method to each scene, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input the characteristics of each scene into the generative AI and have the generative AI execute the application of the appropriate analysis method.

[0094] The verbalization unit can estimate the user's emotions and adjust the verbalization expression based on the estimated emotions. For example, the verbalization unit can capture the user's facial expressions with a camera and estimate the emotions using an emotion estimation algorithm. For example, the verbalization unit can calculate an emotion score based on changes in facial expressions. The verbalization unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the verbalization unit can analyze the tone and speed of the voice and calculate an emotion score. The verbalization unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotions using an emotion estimation algorithm. For example, the verbalization unit can calculate an emotion score based on fluctuations in heart rate. This allows the verbalization expression to be adjusted 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-described processes in the verbalization unit are performed using generative AI. For example, the language processing unit can input user emotion data into the generating AI and have the generating AI adjust the way the language is expressed.

[0095] The verbalization unit can adjust the level of detail in verbalization based on the importance of the visual information. For example, the verbalization unit can perform detailed verbalization in important scenes. For example, the verbalization unit can verbalize visual information in detail in important scenes. The verbalization unit can also perform concise verbalization in scenes of low importance. For example, the verbalization unit can verbalize visual information concisely in scenes of low importance. Furthermore, the verbalization unit can verbalize with an appropriate level of detail in scenes of moderate importance. For example, the verbalization unit can verbalize visual information with an appropriate level of detail in scenes of moderate importance. This makes it possible to adjust the level of detail in verbalization according to the importance of the visual information. Some or all of the above processing in the verbalization unit is performed using a generative AI. For example, the verbalization unit can input the importance of the visual information into the generative AI and have the generative AI perform the adjustment of the level of detail in verbalization.

[0096] The language processing unit can apply different language processing algorithms depending on the context of the video content during the language processing process. For example, in dramas, the language processing unit can perform language processing that emphasizes emotional expression. For instance, it can perform language processing that richly expresses the emotions of the characters in a drama scene. Furthermore, in action movies, the language processing unit can perform language processing that emphasizes the expression of actions. For instance, it can perform language processing that describes the actions of the characters in an action scene in detail. In addition, in documentaries, the language processing unit can perform language processing that emphasizes the expression of facts. For instance, it can perform language processing that accurately expresses the facts in a documentary scene. This enables language processing that is appropriate to the context of the video content. Some or all of the above processing in the language processing unit is performed using a generative AI. For example, the language processing unit can input the context of the video content into the generative AI and have the generative AI apply an appropriate language processing algorithm.

[0097] The verbalization unit can estimate the user's emotions and adjust the length of the verbalization based on the estimated emotions. For example, the verbalization unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the verbalization unit can calculate an emotion score based on changes in facial expressions. The verbalization unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the verbalization unit can analyze the tone and speed of the voice and calculate an emotion score. The verbalization unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the verbalization unit can calculate an emotion score based on fluctuations in heart rate. This allows the length of the verbalization to be adjusted 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-described processes in the verbalization unit are performed using generative AI. For example, the language generation unit can input user emotion data into the generating AI and have the generating AI adjust the length of the resulting verbalization.

[0098] The language processing unit can determine the priority of language processing based on the frequency of occurrence of visual information. For example, the language processing unit can prioritize the language processing of frequently occurring visual information. The language processing unit can also postpone the processing of less frequently occurring visual information. Furthermore, the language processing unit can adjust the order of language processing according to the frequency of occurrence. For example, the language processing unit can adjust the order of language processing of visual information according to the frequency of occurrence. This makes it possible to determine the priority of language processing according to the frequency of occurrence of visual information. Some or all of the above processing in the language processing unit is performed using a generative AI. For example, the language processing unit can input the frequency of occurrence of visual information to the generative AI and have the generative AI perform the determination of the priority of language processing.

[0099] The verbalization unit can adjust the order of verbalization based on the relevance of the visual information. For example, the verbalization unit can prioritize verbalizing important visual information. The verbalization unit can also postpone the verbalization of less relevant visual information. Furthermore, the verbalization unit can adjust the order of verbalization according to relevance. For example, the verbalization unit can adjust the order of verbalization of visual information according to relevance. This makes it possible to adjust the order of verbalization according to the relevance of the visual information. Some or all of the above processing in the verbalization unit is performed using a generative AI. For example, the verbalization unit can input the relevance of the visual information into the generative AI and have the generative AI perform the adjustment of the verbalization order.

[0100] The voice conversion unit can estimate the user's emotions and adjust the tone of the voice conversion based on the estimated emotions. For example, the voice conversion unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the voice conversion unit calculates an emotion score based on changes in facial expressions. The voice conversion unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the voice conversion unit analyzes the tone and speed of the voice and calculates an emotion score. The voice conversion unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the voice conversion unit calculates an emotion score based on fluctuations in heart rate. This makes it possible to adjust the tone of the voice conversion 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 voice conversion unit is performed using generative AI. For example, the voice conversion unit can input user emotion data into the generating AI and have the generating AI adjust the tone of the voice conversion.

[0101] The speech conversion unit can adjust the volume of the speech based on the importance of the verbalized information during speech conversion. For example, the speech conversion unit can emphasize important information during speech conversion. For example, the speech conversion unit can emphasize important visual information during speech conversion. The speech conversion unit can also convert less important information to a lower volume. For example, the speech conversion unit can convert less important visual information to a lower volume. Furthermore, the speech conversion unit can convert information of moderate importance to an appropriate volume. For example, the speech conversion unit can convert visual information of moderate importance to an appropriate volume. This makes it possible to adjust the volume of the speech according to the importance of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the importance of the verbalized information into the generation AI and have the generation AI perform the adjustment of the volume of the speech.

[0102] The audio conversion unit can apply different audio conversion algorithms depending on the genre of the video content during audio conversion. For example, in dramas, the audio conversion unit can perform audio conversion that emphasizes emotional expression. For instance, it can perform audio conversion that richly expresses the emotions of the characters in a drama scene. Furthermore, in action movies, the audio conversion unit can perform audio conversion that emphasizes the expression of actions. For example, it can perform audio conversion that accurately expresses the actions of the characters in an action scene. Additionally, in documentaries, the audio conversion unit can perform audio conversion that emphasizes the expression of facts. For example, it can perform audio conversion that accurately expresses the facts in a documentary scene. This enables audio conversion tailored to the genre of the video content. Some or all of the above processing in the audio conversion unit is performed using a generative AI. For example, the audio conversion unit can input the genre of the video content into the generative AI and have the generative AI apply an appropriate audio conversion algorithm.

[0103] The speech conversion unit can estimate the user's emotions and adjust the speed of speech conversion based on the estimated emotions. For example, the speech conversion unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the speech conversion unit calculates an emotion score based on changes in facial expressions. The speech conversion unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the speech conversion unit analyzes the tone and speed of the voice and calculates an emotion score. The speech conversion unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the speech conversion unit calculates an emotion score based on fluctuations in heart rate. This makes it possible to adjust the speed of speech conversion 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-described processes in the speech conversion unit are performed using generative AI. For example, the voice conversion unit can input user emotion data into the generating AI and have the generating AI adjust the speed of voice conversion.

[0104] The speech conversion unit can determine the priority of speech based on the frequency of occurrence of the verbalized information during speech conversion. For example, the speech conversion unit can prioritize the conversion of frequently occurring information. For example, the speech conversion unit can prioritize the conversion of frequently occurring visual information. The speech conversion unit can also postpone the conversion of less frequently occurring information. For example, the speech conversion unit can postpone the conversion of less frequently occurring visual information. Furthermore, the speech conversion unit can adjust the order of speech conversion according to the frequency of occurrence. For example, the speech conversion unit can adjust the order of speech conversion of visual information according to its frequency of occurrence. This makes it possible to determine the priority of speech based on the frequency of occurrence of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the frequency of occurrence of the verbalized information into the generation AI and have the generation AI perform the determination of speech priority.

[0105] The speech conversion unit can adjust the order of speech based on the relevance of the verbalized information during speech conversion. For example, the speech conversion unit can prioritize the conversion of important information. For example, the speech conversion unit can prioritize the conversion of important visual information. The speech conversion unit can also postpone the conversion of less relevant information. For example, the speech conversion unit can postpone the conversion of less relevant visual information. Furthermore, the speech conversion unit can adjust the order of speech conversion according to relevance. For example, the speech conversion unit can adjust the order of speech conversion of visual information according to relevance. This makes it possible to adjust the order of speech according to the relevance of the verbalized information. Some or all of the above processing in the speech conversion unit is performed using a generation AI. For example, the speech conversion unit can input the relevance of the verbalized information into the generation AI and have the generation AI perform the adjustment of the order of speech.

[0106] The delivery unit can estimate the user's emotions and adjust the method of delivering audio content based on the estimated user emotions. For example, the delivery unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the delivery unit can calculate an emotion score based on changes in facial expressions. The delivery unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the delivery unit can analyze the tone and speed of the voice and calculate an emotion score. The delivery unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, the delivery unit can calculate an emotion score based on fluctuations in heart rate. This makes it possible to adjust the method of delivering audio content 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 delivery unit is performed using generative AI. For example, the service provider can input user emotion data into a generating AI and have the AI ​​adjust the method of delivering audio content.

[0107] The delivery unit can select the optimal delivery method when delivering audio content by referring to the user's past viewing history. For example, the delivery unit can select the optimal delivery method based on the user's past viewing trends. For example, the delivery unit can analyze the user's viewing history and select the optimal delivery method based on the user's past viewing trends. The delivery unit can also select a delivery method that matches the user's preferred genre based on their past viewing history. For example, the delivery unit can analyze the user's viewing history and select a delivery method that matches their preferred genre. Furthermore, the delivery unit can analyze the user's past viewing history and select the most efficient delivery method. For example, the delivery unit can analyze the user's viewing history and select the most efficient delivery method. This makes it possible to select the optimal delivery method based on the user's past viewing history. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's viewing history into AI and have the AI ​​select the optimal delivery method.

[0108] The delivery unit can customize the delivery method when providing audio content according to the genre of the video content. For example, in the case of a drama, the delivery unit can select a delivery method that emphasizes emotional expression. For example, the delivery unit can select a delivery method that emphasizes emotional expression in drama scenes. Also, in the case of an action movie, the delivery unit can select a delivery method that emphasizes action expression. For example, the delivery unit can select a delivery method that emphasizes action expression in action scenes. Furthermore, in the case of a documentary, the delivery unit can select a delivery method that emphasizes factual expression. For example, the delivery unit can select a delivery method that emphasizes factual expression in documentary scenes. This makes it possible to customize the delivery method according to the genre of the video content. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the genre of the video content into the AI ​​and have the AI ​​perform the customization of the delivery method.

[0109] The delivery unit can estimate the user's emotions and adjust the order in which audio content is delivered based on the estimated emotions. For example, the delivery unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the delivery unit can calculate an emotion score based on changes in facial expressions. The delivery unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the delivery unit can analyze the tone and speed of the voice and calculate an emotion score. The delivery unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, the delivery unit can calculate an emotion score based on fluctuations in heart rate. This makes it possible to adjust the order in which audio content is delivered 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 delivery unit is performed using generative AI. For example, the service provider can input user emotion data into a generating AI and have the AI ​​adjust the order in which audio content is delivered.

[0110] The delivery unit can select the optimal delivery method based on the user's device information when delivering audio content. For example, if the user is using a smartphone, the delivery unit can select a delivery method that matches the screen size. For example, the delivery unit can deliver audio content optimized for the smartphone screen size. Also, if the user is using a tablet, the delivery unit can select a delivery method optimized for the larger screen. For example, the delivery unit can deliver audio content optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the delivery unit can select a concise and highly visible delivery method. For example, the delivery unit can deliver audio content optimized for the small screen of a smartwatch. This makes it possible to select the optimal delivery method based on the user's device information. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's device information into AI and have the AI ​​select the optimal delivery method.

[0111] The delivery unit can adjust the delivery method based on the user's listening environment when delivering audio content. For example, if the user is in a quiet environment, the delivery unit can select a detailed delivery method. For example, the delivery unit can deliver detailed audio content in a quiet environment. The delivery unit can also select a concise delivery method if the user is in a noisy environment. For example, the delivery unit can deliver concise audio content in a noisy environment. Furthermore, if the user is on the move, the delivery unit can adjust the delivery method in real time. For example, the delivery unit can deliver the optimal audio content to a user on the move in real time. This makes it possible to adjust the delivery method according to the user's listening environment. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's listening environment into AI and have the AI ​​perform the adjustment of the delivery method.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The audio content creation system can also include a customized audio filtering function based on user preferences. For example, if a user prefers a particular music genre, music of that genre can be filtered to prioritize it. Similarly, if a user prefers a specific voice tone or accent, filtering can be applied to emphasize that tone or accent. Furthermore, if a user prefers a specific sound effect, filtering can be applied to emphasize that sound effect. This allows for the provision of customized audio content tailored to the user's preferences.

[0114] The analysis unit can apply different analysis algorithms to each scene of the video content. For example, it can prioritize motion analysis in action scenes and facial expression analysis in dialogue scenes. It can also prioritize object analysis in landscape scenes. Furthermore, the analysis unit can switch analysis algorithms in real time according to changes in the scene. This enables optimal analysis for each scene.

[0115] The language processing unit can estimate the user's emotions and adjust the language expression based on the estimated emotions. For example, if the user is moved, it can use expressions that emphasize the emotion. Similarly, if the user is excited, it can use expressions that emphasize the excitement. Furthermore, if the user is relaxed, it can use expressions that emphasize relaxation. This makes it possible to provide language that is appropriate to the user's emotions.

[0116] The voice conversion unit can estimate the user's emotions and adjust the tone of the voice conversion based on the estimated emotions. For example, if the user is sad, a tone emphasizing sadness can be used. Similarly, if the user is happy, a tone emphasizing happiness can be used. Furthermore, if the user is angry, a tone emphasizing anger can be used. This enables voice conversion that responds to the user's emotions.

[0117] The delivery unit can estimate the user's emotions and adjust the way audio content is delivered based on those estimated emotions. For example, if the user is relaxed, it can select a delivery method that promotes relaxation. If the user is focused, it can select a delivery method that maintains focus. Furthermore, if the user is tired, it can select a delivery method that reduces fatigue. This makes it possible to deliver optimal audio content tailored to the user's emotions.

[0118] The acquisition unit can determine the priority of auditory information to acquire by referring to the metadata of the video content. For example, it can prioritize the acquisition of important dialogue and sound effects based on the metadata. It can also prioritize the acquisition of music from a specific scene based on the metadata. Furthermore, it can prioritize the acquisition of dialogue from a specific character based on the metadata. This enables efficient acquisition of auditory information by utilizing metadata.

[0119] The analysis unit can optimize its analysis algorithm according to the genre of video content. For example, it can prioritize facial expression analysis for dramas and motion analysis for action movies. It can also prioritize the analysis of scenery and objects for documentaries. Furthermore, the analysis unit can improve analysis accuracy by applying different analysis algorithms for each genre. This enables optimal analysis tailored to each genre.

[0120] The verbalization unit can determine the priority of verbalization based on the frequency of occurrence of visual information. For example, it can prioritize verbalizing frequently occurring visual information. It can also postpone the verbalization of less frequently occurring visual information. Furthermore, it can adjust the order of verbalization according to the frequency of occurrence. This enables efficient verbalization in accordance with the frequency of occurrence of visual information.

[0121] The speech conversion unit can adjust the volume of the speech based on the importance of the information being spoken. For example, important information can be emphasized during speech conversion. Less important information can be converted more subtly. Furthermore, information of moderate importance can be converted with an appropriate volume. This makes it possible to adjust the volume of the speech according to the importance of the information being spoken.

[0122] The delivery unit can select the optimal delivery method based on the user's device information. For example, if the user is using a smartphone, it can select a delivery method that matches the screen size. If the user is using a tablet, it can select a delivery method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can select a concise and highly visible delivery method. This makes it possible to select the optimal delivery method based on the user's device information.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The acquisition unit acquires auditory information from the video content. The acquisition unit can acquire auditory information such as dialogue, music, and sound effects from the video content. The acquisition unit can collect audio using a microphone or extract auditory information directly from the audio track of the video content. It can also convert the audio of the video content into text data using speech recognition technology. Step 2: The analysis unit analyzes the visual information contained in the video based on the auditory information acquired by the acquisition unit. The analysis unit can analyze visual information such as the facial expressions of characters and the scenery contained in the video. The analysis unit can analyze the facial expressions of characters using face recognition technology and analyze the scenery using scene analysis technology. Furthermore, it can also identify objects in the video using object recognition technology. Step 3: The language processing unit translates the visual information analyzed by the analysis unit into language. The language processing unit can convert the visual information into text data using natural language processing techniques. The language processing unit can use text generation AI to convert the visual information into natural language and can employ algorithms to generate grammatically correct sentences. Furthermore, it can also employ techniques to generate semantically consistent sentences. Step 4: The speech conversion unit converts the visual information verbalized by the language conversion unit into speech. The speech conversion unit can convert text data into speech data using speech synthesis technology. The speech conversion unit can use speech synthesis AI to generate natural-sounding speech and can employ techniques to adjust intonation and accent. Furthermore, it can also use algorithms to improve speech fluency. Step 5: The delivery unit combines the audio converted by the speech conversion unit with auditory information to provide audio content. The delivery unit can provide audio content through streaming services. The delivery unit can distribute audio content through web applications and mobile applications. It can also provide audio content in download format. Furthermore, it can provide audio content in podcast format.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the acquisition unit, analysis unit, language processing unit, speech conversion unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit can collect sound using the microphone 38B of the smart device 14. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the visual information contained in the video. The language processing unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the visual information into natural language. The speech conversion unit is implemented by the control unit 46A of the smart device 14 and converts the languaged visual information into speech. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides audio content by combining speech and auditory information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

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

[0132] The 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.

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

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

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

[0136] Figure 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.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0139] In the 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.

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

[0141] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0143] The data processing system 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.

[0144] Each of the multiple elements described above, including the acquisition unit, analysis unit, language processing unit, speech conversion unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit can collect sound using the microphone 238 of the smart glasses 214. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the visual information contained in the image. The language processing unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the visual information into natural language. The speech conversion unit is implemented by the control unit 46A of the smart glasses 214 and converts the languaged visual information into speech. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides audio content by combining speech and auditory information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

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

[0148] The 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.

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

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (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).

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

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the acquisition unit, analysis unit, language processing unit, speech conversion unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit can collect sound using the microphone 238 of the headset terminal 314. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the visual information contained in the video. The language processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the visual information into natural language. The speech conversion unit is implemented by the control unit 46A of the headset terminal 314 and converts the languaged visual information into speech. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides audio content by combining speech and auditory information. 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.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements described above, including the acquisition unit, analysis unit, language processing unit, speech conversion unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit can collect sound using the microphone 238 of the robot 414. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the visual information contained in the video. The language processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the visual information into natural language. The speech conversion unit is implemented by the control unit 46A of the robot 414 and converts the languaged visual information into speech. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides audio content by combining speech and auditory information. 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) An acquisition unit that acquires auditory information from video content, Based on the auditory information acquired by the aforementioned acquisition unit, an analysis unit analyzes the visual information contained in the video, A language processing unit that translates the visual information analyzed by the aforementioned analysis unit into language, A speech conversion unit that converts the visual information verbalized by the language conversion unit into speech, The system includes a providing unit that provides audio content by combining the voice converted by the voice conversion unit with auditory information. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze visual information such as the facial expressions of characters and the scenery contained in the video. The system described in Appendix 1, characterized by the features described herein. (Note 3) The language processing unit, The aforementioned analysis unit converts the analyzed visual information into natural language. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned voice conversion unit is The aforementioned language processing unit converts the verbalized visual information into natural-sounding speech. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, The audio content is provided by combining the voice converted by the aforementioned voice conversion unit with auditory information. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Provide audio content with commentary through streaming services. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of auditory information acquisition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, The auditory information to be acquired is filtered according to the type of video content. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring auditory information, noise reduction is performed to obtain clear audio data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, It estimates the user's emotions and determines the priority of auditory information to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring auditory information, the system prioritizes acquiring highly relevant information based on the user's viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When acquiring auditory information, use subtitle information from video content in conjunction with it. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the method of analyzing visual information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The analysis algorithm is optimized according to the genre of the video content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing visual information, the analysis accuracy is adjusted according to the video's frame rate. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing visual information, referencing the metadata of the video content improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing visual information, different analysis methods are applied to each scene of the video content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The language processing unit, It estimates the user's emotions and adjusts the way it expresses those emotions based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The language processing unit, When verbalizing information, adjust the level of detail based on the importance of the visual information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The language processing unit, When translating into language, different language translation algorithms are applied depending on the context of the video content. The system described in Appendix 1, characterized by the features described herein. (Note 22) The language processing unit, It estimates the user's emotions and adjusts the length of the verbalization based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The language processing unit, When verbalizing information, prioritize verbalization based on the frequency of visual information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The language processing unit, When verbalizing, adjust the order of verbalization based on the relevance of visual information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned voice conversion unit is It estimates the user's emotions and adjusts the tone of the voice conversion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned voice conversion unit is During speech conversion, the volume of the speech is adjusted based on the importance of the information being spoken. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned voice conversion unit is When converting audio, different audio conversion algorithms are applied depending on the genre of the video content. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned voice conversion unit is It estimates the user's emotions and adjusts the speed of speech conversion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned voice conversion unit is During speech conversion, the priority of speech is determined based on the frequency of occurrence of the verbalized information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned voice conversion unit is During speech conversion, the order of speech is adjusted based on the relevance of the verbalized information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, It estimates the user's emotions and adjusts how audio content is delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, When providing audio content, the system selects the optimal delivery method by referring to the user's past listening history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned supply unit is, When providing audio content, customize the delivery method according to the genre of the video content. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, It estimates the user's emotions and adjusts the order in which audio content is delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned supply unit is, When providing audio content, the optimal delivery method is selected based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned supply unit is, When providing audio content, the delivery method will be adjusted based on the user's listening environment. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 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. An acquisition unit that acquires auditory information from video content, Based on the auditory information acquired by the aforementioned acquisition unit, an analysis unit analyzes the visual information contained in the video, A language processing unit that translates the visual information analyzed by the aforementioned analysis unit into language, A speech conversion unit that converts the visual information verbalized by the language conversion unit into speech, The system includes a providing unit that provides audio content by combining the voice converted by the voice conversion unit with auditory information. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze visual information such as the facial expressions of characters and the scenery contained in the video. The system according to feature 1.

3. The language processing unit, The aforementioned analysis unit converts the analyzed visual information into natural language. The system according to feature 1.

4. The aforementioned voice conversion unit is The aforementioned language processing unit converts the verbalized visual information into natural-sounding speech. The system according to feature 1.

5. The aforementioned supply unit is, The audio content is provided by combining the voice converted by the aforementioned voice conversion unit with auditory information. The system according to feature 1.

6. The aforementioned supply unit is, Provide audio content with commentary through streaming services. The system according to feature 1.

7. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of auditory information acquisition based on the estimated emotions. The system according to feature 1.

8. The acquisition unit is, The auditory information to be acquired is filtered according to the type of video content. The system according to feature 1.

9. The acquisition unit is, When acquiring auditory information, noise reduction is performed to obtain clear audio data. The system according to feature 1.

10. The acquisition unit is, It estimates the user's emotions and determines the priority of auditory information to acquire based on the estimated user emotions. The system according to feature 1.

Images