system

Abstract

We provide a system that allows you to create professional music without any hassle. [Solution] The system includes a speech synthesis means that analyzes the speech features input by the user and generates speech data by combining them with existing music data selected based on that analysis. The system includes a video generation means for generating a music video that integrates background music and visual content using the audio data generated by the aforementioned speech synthesis means, and a distribution means for distributing the music video to a user terminal.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Existing music production processes have problems such as high operation difficulty, high time and cost, which pose a high threshold for general users. Also, due to the need for advanced technology and specialized knowledge, it is difficult for anyone to easily produce high-quality music. There is a need for a method to lower these barriers and produce professional music without much effort.

Means for Solving the Problems

[0005] This invention provides a speech synthesis means that analyzes voice features input by a user and generates voice data by combining them with existing music data selected based on that analysis. Furthermore, it provides a system that includes a video generation means that generates a music video integrating background music and visual content using the generated voice data, and a distribution means for delivering the music video to a user terminal, thereby simplifying the music production process. As a result, users can easily generate their own music content and produce high-quality music videos in less time and at a lower cost.

[0006] A "user" is an end-user who uses the system to input audio data and generate music videos by combining it with existing music data.

[0007] "Speech features" are data that represents the characteristics of speech, such as pitch, timing, and timbre, extracted from input speech data.

[0008] "Existing music data" refers to a dataset of musical works included in the library, which users can select as the basis for speech synthesis.

[0009] "Speech synthesis means" refers to a technical means for generating new speech data based on the user's speech characteristics and existing music data.

[0010] "Video generation means" refers to a technical means that integrates audio data generated by a speech synthesis means with background music and visual content to create a final music video.

[0011] "Distribution method" refers to the communication means and protocols used to transmit generated music videos to a user's device. [Brief explanation of the drawing]

[0012] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. [[ID=I4]]

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like. [[ID=1x]]

[0019] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] The 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.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system that enables users to efficiently generate high-quality music videos using individual audio data. This system is mainly composed of a combination of speech synthesis means, video generation means, and distribution means.

[0034] First, the user records audio data on their device via a dedicated application or web platform and uploads it to the system. At the same time, the user can select existing music data from a provided library. The device then sends this data to the server.

[0035] The server analyzes the features of the user's voice and prepares it to be combined with selected music data. This process involves using speech synthesis technology to match the user's voice to the melody line of the selected song. Specifically, the server matches the user's recorded voice to an existing pop song, generating audio that sounds as if the user is professionally singing the song.

[0036] In the video generation phase, the server adds existing background music to the generated audio and integrates appropriate visual content. This process generates the completed music video. The terminal receives the generated music video from the server and provides it to the user in a viewable format.

[0037] Users can not only enjoy these music videos themselves, but also share them using platforms such as social media. This system allows users to easily create their own musical works without having to worry about complicated procedures or high costs.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] Users record their voices using a dedicated application or web platform and save them as audio data files. They then upload this audio data from their device to the system.

[0041] Step 2:

[0042] The user selects an existing song they want to use from the music library provided within the system. The selected song information is sent to the server via the terminal.

[0043] Step 3:

[0044] The server analyzes the audio data received from the user and extracts audio features such as pitch, timing, and timbre. This prepares the basic data needed to determine the compatibility with the selected music data.

[0045] Step 4:

[0046] Based on the analyzed speech features, the server uses speech synthesis technology to generate audio data that matches the user's voice to the melody line of the selected song. At this stage, audio adjustments and effects are also applied.

[0047] Step 5:

[0048] The server combines the generated audio data with existing background music and adds visual content to create a music video. This visual content includes lyrics, theme-specific images, and video clips.

[0049] Step 6:

[0050] The server encodes the generated music video and converts it into a format that can be sent to the user's device.

[0051] Step 7:

[0052] The device receives music videos sent from the server and displays them to the user in a viewable format. Users can not only watch these videos but also share them on social media and other platforms.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] Modern users want to easily and efficiently generate high-quality music content using their individual voices. However, existing technologies require advanced expertise and high costs, making them inaccessible to individuals. Furthermore, the complexity of improving sound quality and integrating visual elements makes it difficult for users to create content they are satisfied with.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes a generation means that analyzes voice information input by the user and generates voice information by combining it with existing music data selected based on that analysis; a synthesis means that uses the voice information generated by the generation means to generate music content that integrates background sounds and visual information; and a supply means for supplying the music content to the user's device. This enables the user to generate and listen to high-quality music content without experiencing complex procedures or technical hurdles.

[0058] "Voice information" refers to the voice data entered by the user, and its features are the subject of analysis.

[0059] "Generation means" refers to processing means for generating synthesized speech by combining analyzed speech information with existing music data.

[0060] A "synthesis method" is a means that integrates background sounds and visual information into the generated audio to complete the music content.

[0061] "Supply means" refers to processing means that provide completed music content to the user's device and make it available for listening.

[0062] A "collection" refers to a library of existing music data that users can select, offering a variety of choices.

[0063] "Adjustment means" refers to processing means that have the function of automatically adjusting the pitch and temporal arrangement of the user's voice information to match the music data.

[0064] This system is a platform for users to generate music content using their own voice. First, users record voice information using a dedicated application or web platform and upload it from their device to the server along with selected existing music data. Here, users can select from a large number of music files from their library.

[0065] The server analyzes the received audio information and extracts its features (such as pitch and tempo). This analysis utilizes speech analysis technology powered by a generative AI model. Subsequently, the server generates audio information by matching the analyzed audio information to the melody line of the selected music data. This generation process is carried out by an audio adjustment mechanism that automatically adjusts the pitch and temporal placement of sounds. An example of a prompt message is an instruction such as, "Record user voice and combine it with the selected song to generate high-quality music."

[0066] Next, the server integrates the generated audio information with visual information and background sounds to form music content. At this time, the visual information is dynamically changed according to the emotion and tempo of the audio, resulting in the creation of high-quality music content.

[0067] The device receives the completed music content from the server and provides it to the user. The user can not only enjoy this content personally, but also share it with others via an online platform.

[0068] This system allows users to easily and efficiently create their own music content, even without specialized skills.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The user records audio using a dedicated application or web platform. The recorded data is saved to the device along with selected existing music data. This process provides an interface for the user to select music data from their library along with their own audio. The input is the user's audio data and the selected music data, and the output is a combination of these data.

[0072] Step 2:

[0073] The device sends the audio data recorded by the user and the selected music data to the server. This prepares the server for data processing. The input is the audio and music data stored on the device, and the output is the data sent to the server.

[0074] Step 3:

[0075] The server receives the transmitted audio data and analyzes its features. A generative AI model is used to extract the pitch, tempo, and voice quality of the audio data. The result of the analysis is the structural features of this audio data. The input is the audio data received by the server, and the output is the analyzed audio features.

[0076] Step 4:

[0077] The server integrates the voice with selected music data based on the features of the analyzed voice data. During this process, voice adjustment mechanisms are used to generate voice that matches the user's voice to the music's melody. Specifically, the pitch and timing of the voice are automatically adjusted. The input consists of voice features and selected music data, and the output is the integrated voice data.

[0078] Step 5:

[0079] The server uses the generated audio to create music content that integrates visual information and background sounds. The visual information is dynamically selected based on the emotion and tempo of the audio data. The input is integrated audio data, and the output is the completed music content.

[0080] Step 6:

[0081] The device receives completed music content from the server and provides it to the user. The user can listen to this content and share it on platforms such as social media as needed. The input is music content from the server, and the output is content converted into a format viewable by the user.

[0082] (Application Example 1)

[0083] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0084] There is a lack of a platform that allows users to efficiently create high-quality music videos using their own voices and easily share them. Traditional methods require high levels of expertise and cost for voice synthesis and video generation, making them inaccessible to the average user. Furthermore, they lack features for smoothly sharing the generated content.

[0085] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0086] In this invention, the server includes a speech synthesis means that analyzes audio features input by the user and generates audio information by combining them with selected music information; a video generation means that uses the audio information generated by the speech synthesis means to integrate supplementary information and visual information to generate video information; and a distribution means for distributing the video information to an end-user device. This enables users to create and share professional music videos without requiring specialized knowledge or incurring high costs.

[0087] "Speech features" are characteristic elements extracted from speech data, and include information such as pitch, intensity, and voice quality.

[0088] "Song information" refers to data related to music, which may include melody, rhythm, and lyrics.

[0089] "Audio information" refers to data generated based on audio features, and specifically to synthesized data produced through speech synthesis.

[0090] "Speech synthesis means" refers to a process and apparatus for generating speech information based on speech features and music information.

[0091] "Supplemental information" refers to background music or sound effects added to enhance or supplement audio information.

[0092] "Visual information" refers to visual content such as images, videos, and animations used to constitute video information.

[0093] "Video generation means" refers to a process and apparatus for generating video information by combining audio information, supplementary information, and visual information.

[0094] "End-user device" refers to a device used by a user to view or interact with the final generated content, and includes smartphones and tablets.

[0095] "Distribution means" refers to the process and equipment for transmitting generated video information to end-user devices.

[0096] To implement this invention, the user operates a dedicated application using their smartphone or tablet. First, the user activates an interface for recording voice on their smartphone and records their voice. Once recording is complete, the application sends the voice data to a server in the cloud. The server has voice processing libraries such as Google® Cloud Speech-to-Text and WaveNet installed, which analyze the user's voice features and combine them with selected music information. Based on the resulting voice information, supplementary and visual information is integrated, and a video is generated using tools such as FFmpeg.

[0097] The generated video is transmitted to the end-user's device using a distribution method, and the user can view it or share it on social media. Specifically, for example, a user can create a professional video of themselves covering a hit song with their own voice and share it with friends for enjoyment. An example of a prompt message in this case would be: "Synthesize the audio files recorded by the user to create a professional soundtrack set to the song 'XYZ Song,' add visual effects, and generate a video."

[0098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0099] Step 1:

[0100] The user launches an application on their smartphone and uses the voice recording function to record their voice. At this stage, the user's voice is saved on the device as an audio data file.

[0101] Step 2:

[0102] The device sends the recorded audio data to a server located in the cloud. To ensure security, the data is encrypted and stored on the server as audio data.

[0103] Step 3:

[0104] The server uses the Google Cloud Speech-to-Text service as input to analyze the audio features of the received audio data. As a result, it outputs feature data including the pitch and tempo of the audio.

[0105] Step 4:

[0106] The server runs a speech synthesis model such as WaveNet to combine speech features with user-selected song information. This results in the output of speech information that matches the melody line of the song.

[0107] Step 5:

[0108] The server uses the generated audio information to integrate the audio and visual elements using the video generation tool FFmpeg. In this step, supplementary information such as background music and animation is used to create a visually appealing video.

[0109] Step 6:

[0110] The server sends the completed music video data back to the device, which receives it and makes it available for the user to view. The video plays within the device's application, allowing the user to enjoy the content.

[0111] Step 7:

[0112] Users can send videos generated using the application's sharing function via social media and messaging platforms. This enables widespread sharing of the generated content.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention realizes a system that provides more personalized music videos by recognizing emotions from the user's voice data and reflecting them in the selected music and generated content. In addition to voice synthesis means, video generation means, and distribution means, this system utilizes an emotion engine that analyzes the user's emotions in real time and optimizes the content based on that analysis.

[0115] First, the user records their voice via a device and uploads this audio data to the system. At the same time, the user selects a song of their choice from the music library. This audio data is sent to a server, which uses an emotion engine to identify emotions from the user's voice. For example, if the server recognizes that the user's voice contains the emotion of "joy," it uses this information to generate audio data that reflects that emotion using speech synthesis.

[0116] Next, the server adjusts the tempo of the music and the selection of instruments based on the emotional information obtained from the emotion engine, and also modifies the colors and effects in the video content. This process generates a music video that matches the user's emotions. For example, if the system recognizes that the user is feeling "sadness," the music will become calmer, and the visuals will be updated with more subdued colors to match.

[0117] The generated music video is encoded on the server and sent to the device. Users can then view it on their device and share it on social media, etc. This system allows users to easily enjoy more personalized music based on their individual emotions.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The user records their own voice and saves this audio data to their device. Then, the user uploads the recorded audio from their device to the system.

[0121] Step 2:

[0122] The user selects their preferred song from the music library provided by the system. The selected song information is sent from the terminal to the server.

[0123] Step 3:

[0124] The server uses an emotion engine to analyze audio features such as pitch, rhythm, and timbre on the audio data received from the user, and also recognizes the user's emotions from the audio.

[0125] Step 4:

[0126] The server performs speech synthesis necessary for generating music videos based on the recognized emotion information. It adjusts the tempo and melody of the music and applies effects according to the target emotion.

[0127] Step 5:

[0128] The server adds background music to the data obtained through speech synthesis and processes the visual content to resonate with the user's emotions. As a result, colors and visual effects corresponding to emotions are reflected in the music video.

[0129] Step 6:

[0130] The server encodes the generated music video and prepares it for distribution in a format playable on the user's device.

[0131] Step 7:

[0132] The device receives music videos streamed from the server and displays them to the user in an instantly viewable format. After watching the videos, users can share them on social media or other platforms as needed to spread their emotional expression.

[0133] (Example 2)

[0134] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0135] Conventional technologies have made it difficult to easily generate personalized media content that reflects user emotions. In particular, it has been impossible to analyze a user's actual emotions through voice and achieve consistent harmony of music and visuals based on these emotions. This has been a major obstacle to improving the user experience.

[0136] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0137] In this invention, the server includes an analysis means for identifying emotions from the user's speech, a speech synthesis means for generating audio data by combining it with music data, and a generation means for adjusting and generating music and visual characteristics. This makes it possible to automatically generate personalized music videos that respond to the user's emotions, thereby improving the user experience.

[0138] A "user" is an entity that uses a system to input voice and generate personalized media content.

[0139] "An analytical means for identifying emotions" refers to a technology that analyzes a user's voice and identifies the emotions contained within that voice.

[0140] "Speech synthesis means" is a technology that generates new speech data by integrating analyzed emotional information with other music data.

[0141] "Generation means" refers to a technology that uses data obtained from speech synthesis means to adjust and integrate music and visual characteristics to create media content.

[0142] "Distribution means" refers to technology that has the function of transmitting generated media content to a user's communication device.

[0143] A "data collection" is a database containing multiple existing songs that users can select from.

[0144] "Voice adjustment means" refers to technology that automatically adjusts the pitch and timing of voice data to match the user's emotional information.

[0145] This system identifies emotions through a user's voice and generates personalized media content based on those emotions. Users first record audio data using their own devices and upload it to the system. During this process, users can also select their preferred music from the data set. The server receives the uploaded audio data and uses analysis tools to identify emotions. These analysis tools utilize speech machine learning algorithms and natural language processing techniques.

[0146] Based on the analyzed emotional information, the server uses speech synthesis to integrate music and audio data that correspond to the user's emotions, generating new audio output. A generative AI model is used in this process. Next, the generative means adjusts characteristics such as the tempo of the music and the color tone of the visuals to match the emotions, completing the final media content. This media content is delivered to the user's device, and the user can view or share the content.

[0147] For example, if a user provides audio expressing a desire to relax, the system will analyze the audio and generate a video that combines relaxing music with calming visuals. Another example of a prompt to input to the generation AI model would be, "Express your desire to relax in audio and generate a video with calming music and simple visuals."

[0148] These features are implemented by their respective hardware and software components, aiming to provide users with new music and visual experiences.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The user records audio data using their device. The audio recorded by the user includes elements that express specific emotions. This audio data is saved as a digital file on the device and stored in a temporary cache. The input data is raw audio data, and the result is an audio file ready to be sent to the server as output.

[0152] Step 2:

[0153] The user uploads audio data recorded via their device to the server. Simultaneously, the user selects a preferred song from the system's data collection. The selected song is also sent to the server. The input consists of the audio file and the selected song information, while the output is the status of the audio data's reception on the server.

[0154] Step 3:

[0155] The server receives the uploaded audio data and begins processing it with an analysis tool that identifies emotions. The analysis tool uses an audio machine learning algorithm to extract features from the audio data (such as tone, pitch, and tempo) and identify the user's emotions. The input is the audio data, and the output is the identified emotion information.

[0156] Step 4:

[0157] The server uses speech synthesis to integrate the identified emotion information with the selected song. This generates new voice data that corresponds to the emotion. A generative AI model is used in this process to create voice output that reflects the emotion. The input is emotion information and song data, and the output is the integrated voice data.

[0158] Step 5:

[0159] The server uses a generation mechanism to adjust the music and visual characteristics based on the audio data created in the previous step, generating the final media content. The tempo of the music and the color tones of the visuals are adjusted to match the identified emotion. The input is integrated audio data, and the output is the completed media content.

[0160] Step 6:

[0161] The server encodes the generated media content and delivers it to the user's terminal. During encoding, the optimal format and compression method are selected to ensure efficient transfer. The input is media content, and the output is a media file viewable on the user's terminal.

[0162] Step 7:

[0163] Users view media content received on their devices. After viewing, if they like the content, they can share it via social media, etc. The input is the media file received by the user, and the output is the experience of playing the content.

[0164] (Application Example 2)

[0165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0166] The challenge is to create a system that generates content reflecting individual emotions based on the user's voice data, allowing them to enjoy a more personalized music experience.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes an emotion engine means that analyzes emotions from a user's voice data and generates personalized existing music data and video data selected based on that emotion data; a content generation means that generates integrated music and visual content using the voice data and video data that reflect the emotion information generated by the emotion engine means; and a communication means for distributing the integrated content to a communication terminal. This enables users to view and share personalized music videos that are tailored to their emotions.

[0169] "Audio data" is a collection of acoustic signals generated by a user's speech or voice.

[0170] An "emotion engine means" is a system or device for analyzing voice data to identify the user's emotions and generating data based on the identification results.

[0171] A "content generation method" is a system or device that generates new media by integrating music and visual elements based on emotional information.

[0172] "Communication means" refers to a system or device for transmitting generated digital content to another device via a network.

[0173] A "communication terminal" is a device used by users to receive and display digital content, and includes smartphones and tablets.

[0174] To realize this invention, the system first involves the user performing voice input using the terminal's microphone. The terminal uploads the recorded voice data to a server. The server analyzes the emotions from the voice data using an emotion engine and digitizes the results. This analysis uses speech recognition software (e.g., IBM Watson® Tone Analyzer). Based on the analyzed emotion information, a content generation means generates personalized content incorporating music and visual elements. This generation process utilizes video editing software APIs (e.g., Adobe Premiere Pro API). Finally, the generated content is sent from the server to the communication terminal, making it available for the user to view. Internet connectivity is used for this communication.

[0175] For example, if a user says "I'm feeling great today," the server's emotion engine identifies this as "joy" and generates a music video combining upbeat music and cheerful visuals.

[0176] Examples of prompts for a generative AI model include the following:

[0177] "When a user is experiencing feelings of joy, generate music and visuals that match those feelings. The music should be upbeat, and the visuals should use bright colors."

[0178] In this way, users can enjoy personalized content that matches their own emotions.

[0179] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0180] Step 1:

[0181] The user inputs voice using the device. The device records the user's voice using its built-in microphone. This recorded data is saved as a digital audio file. As a result, the audio data becomes the input.

[0182] Step 2:

[0183] The terminal uploads the recorded audio data to the server. Here, the audio data is transferred to the server via a communication protocol between devices. The audio data is stored on the server and becomes the input for the next calculation process.

[0184] Step 3:

[0185] The server uses an emotion engine to analyze voice data and identify the user's emotions. A speech recognition API (e.g., IBM Watson Tone Analyzer) is used to identify emotions by analyzing the pitch and tone of the voice from the input voice data. Emotion labels (e.g., joy, sadness) are generated as output.

[0186] Step 4:

[0187] The server utilizes the acquired emotion data to provide emotional information to the content generation engine. The engine references video data and music libraries to select music and visual effects that match the emotion. Digital content is created using a content generation API (e.g., Adobe Premiere Pro API). As output, a personalized music video based on the specific emotion is generated.

[0188] Step 5:

[0189] The server encodes the generated content and streams it to the user's communication device. The encoded data enables efficient data transfer and supports smooth playback on the device. The user can complete the experience by viewing this content. Once the digital content is sent to the device, its output is provided visually.

[0190] This process allows users to receive and enjoy personalized content that reflects their own emotions.

[0191] 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.

[0192] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0193] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0194] [Second Embodiment]

[0195] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0196] 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.

[0197] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0198] 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.

[0199] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0200] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0201] 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.

[0202] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0203] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0204] The 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.

[0205] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0206] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0207] This invention provides a system that enables users to efficiently generate high-quality music videos using individual audio data. This system is mainly composed of a combination of speech synthesis means, video generation means, and distribution means.

[0208] First, the user records audio data on their device via a dedicated application or web platform and uploads it to the system. At the same time, the user can select existing music data from a provided library. The device then sends this data to the server.

[0209] The server analyzes the features of the user's voice and prepares it to be combined with selected music data. This process involves using speech synthesis technology to match the user's voice to the melody line of the selected song. Specifically, the server matches the user's recorded voice to an existing pop song, generating audio that sounds as if the user is professionally singing the song.

[0210] In the video generation phase, the server adds existing background music to the generated audio and integrates appropriate visual content. This process generates the completed music video. The terminal receives the generated music video from the server and provides it to the user in a viewable format.

[0211] Users can not only enjoy these music videos themselves, but also share them using platforms such as social media. This system allows users to easily create their own musical works without having to worry about complicated procedures or high costs.

[0212] The following describes the processing flow.

[0213] Step 1:

[0214] Users record their voices using a dedicated application or web platform and save them as audio data files. They then upload this audio data from their device to the system.

[0215] Step 2:

[0216] The user selects an existing song they want to use from the music library provided within the system. The selected song information is sent to the server via the terminal.

[0217] Step 3:

[0218] The server analyzes the audio data received from the user and extracts audio features such as pitch, timing, and timbre. This prepares the basic data needed to determine the compatibility with the selected music data.

[0219] Step 4:

[0220] Based on the analyzed speech features, the server uses speech synthesis technology to generate audio data that matches the user's voice to the melody line of the selected song. At this stage, audio adjustments and effects are also applied.

[0221] Step 5:

[0222] The server combines the generated audio data with existing background music and adds visual content to create a music video. This visual content includes lyrics, theme-specific images, and video clips.

[0223] Step 6:

[0224] The server encodes the generated music video and converts it into a format that can be sent to the user's device.

[0225] Step 7:

[0226] The device receives music videos sent from the server and displays them to the user in a viewable format. Users can not only watch these videos but also share them on social media and other platforms.

[0227] (Example 1)

[0228] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0229] Modern users want to easily and efficiently generate high-quality music content using their individual voices. However, existing technologies require advanced expertise and high costs, making them inaccessible to individuals. Furthermore, the complexity of improving sound quality and integrating visual elements makes it difficult for users to create content they are satisfied with.

[0230] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0231] In this invention, the server includes a generation means that analyzes voice information input by the user and generates voice information by combining it with existing music data selected based on that analysis; a synthesis means that uses the voice information generated by the generation means to generate music content that integrates background sounds and visual information; and a supply means for supplying the music content to the user's device. This enables the user to generate and listen to high-quality music content without experiencing complex procedures or technical hurdles.

[0232] "Voice information" refers to the voice data entered by the user, and its features are the subject of analysis.

[0233] "Generation means" refers to processing means for generating synthesized speech by combining analyzed speech information with existing music data.

[0234] A "synthesis method" is a means that integrates background sounds and visual information into the generated audio to complete the music content.

[0235] "Supply means" refers to processing means that provide completed music content to the user's device and make it available for listening.

[0236] A "collection" refers to a library of existing music data that users can select, offering a variety of choices.

[0237] "Adjustment means" refers to processing means that have the function of automatically adjusting the pitch and temporal arrangement of the user's voice information to match the music data.

[0238] This system is a platform for users to generate music content using their own voice. First, users record voice information using a dedicated application or web platform and upload it from their device to the server along with selected existing music data. Here, users can select from a large number of music files from their library.

[0239] The server analyzes the received audio information and extracts its features (such as pitch and tempo). This analysis utilizes speech analysis technology powered by a generative AI model. Subsequently, the server generates audio information by matching the analyzed audio information to the melody line of the selected music data. This generation process is carried out by an audio adjustment mechanism that automatically adjusts the pitch and temporal placement of sounds. An example of a prompt message is an instruction such as, "Record user voice and combine it with the selected song to generate high-quality music."

[0240] Next, the server integrates the generated audio information with visual information and background sounds to form music content. At this time, the visual information is dynamically changed according to the emotion and tempo of the audio, resulting in the creation of high-quality music content.

[0241] The device receives the completed music content from the server and provides it to the user. The user can not only enjoy this content personally, but also share it with others via an online platform.

[0242] This system allows users to easily and efficiently create their own music content, even without specialized skills.

[0243] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0244] Step 1:

[0245] The user records audio using a dedicated application or web platform. The recorded data is saved to the device along with selected existing music data. This process provides an interface for the user to select music data from their library along with their own audio. The input is the user's audio data and the selected music data, and the output is a combination of these data.

[0246] Step 2:

[0247] The device sends the audio data recorded by the user and the selected music data to the server. This prepares the server for data processing. The input is the audio and music data stored on the device, and the output is the data sent to the server.

[0248] Step 3:

[0249] The server receives the transmitted audio data and analyzes its features. A generative AI model is used to extract the pitch, tempo, and voice quality of the audio data. The result of the analysis is the structural features of this audio data. The input is the audio data received by the server, and the output is the analyzed audio features.

[0250] Step 4:

[0251] The server integrates the voice with selected music data based on the features of the analyzed voice data. During this process, voice adjustment mechanisms are used to generate voice that matches the user's voice to the music's melody. Specifically, the pitch and timing of the voice are automatically adjusted. The input consists of voice features and selected music data, and the output is the integrated voice data.

[0252] Step 5:

[0253] The server uses the generated audio to create music content that integrates visual information and background sounds. The visual information is dynamically selected based on the emotion and tempo of the audio data. The input is integrated audio data, and the output is the completed music content.

[0254] Step 6:

[0255] The device receives completed music content from the server and provides it to the user. The user can listen to this content and share it on platforms such as social media as needed. The input is music content from the server, and the output is content converted into a format viewable by the user.

[0256] (Application Example 1)

[0257] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0258] There is a lack of a platform that allows users to efficiently create high-quality music videos using their own voices and easily share them. Traditional methods require high levels of expertise and cost for voice synthesis and video generation, making them inaccessible to the average user. Furthermore, they lack features for smoothly sharing the generated content.

[0259] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0260] In this invention, the server includes a speech synthesis means that analyzes audio features input by the user and generates audio information by combining them with selected music information; a video generation means that uses the audio information generated by the speech synthesis means to integrate supplementary information and visual information to generate video information; and a distribution means for distributing the video information to an end-user device. This enables users to create and share professional music videos without requiring specialized knowledge or incurring high costs.

[0261] "Speech features" are characteristic elements extracted from speech data, and include information such as pitch, intensity, and voice quality.

[0262] "Song information" refers to data related to music, which may include melody, rhythm, and lyrics.

[0263] "Audio information" refers to data generated based on audio features, and specifically to synthesized data produced through speech synthesis.

[0264] "Speech synthesis means" refers to a process and apparatus for generating speech information based on speech features and music information.

[0265] "Supplemental information" refers to background music or sound effects added to enhance or supplement audio information.

[0266] "Visual information" refers to visual content such as images, videos, and animations used to constitute video information.

[0267] "Video generation means" refers to a process and apparatus for generating video information by combining audio information, supplementary information, and visual information.

[0268] "End-user device" refers to a device used by a user to view or interact with the final generated content, and includes smartphones and tablets.

[0269] "Distribution means" refers to the process and equipment for transmitting generated video information to end-user devices.

[0270] To implement this invention, the user operates a dedicated application using their smartphone or tablet. First, the user activates an interface for recording voice on their smartphone and records their voice. Once recording is complete, the application sends the voice data to a server in the cloud. The server has voice processing libraries such as Google Cloud Speech-to-Text and WaveNet installed, which analyze the user's voice features and combine them with selected music information. Based on the resulting voice information, supplementary and visual information is integrated, and a video is generated using tools such as FFmpeg.

[0271] The generated video is transmitted to the end-user's device using a distribution method, and the user can view it or share it on social media. Specifically, for example, a user can create a professional video of themselves covering a hit song with their own voice and share it with friends for enjoyment. An example of a prompt message in this case would be: "Synthesize the audio files recorded by the user to create a professional soundtrack set to the song 'XYZ Song,' add visual effects, and generate a video."

[0272] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0273] Step 1:

[0274] The user launches an application on their smartphone and uses the voice recording function to record their voice. At this stage, the user's voice is saved on the device as an audio data file.

[0275] Step 2:

[0276] The device sends the recorded audio data to a server located in the cloud. To ensure security, the data is encrypted and stored on the server as audio data.

[0277] Step 3:

[0278] The server uses the Google Cloud Speech-to-Text service with the received voice data as input to analyze the features of the voice. As a result, it outputs feature data including features such as the pitch and tempo of the voice.

[0279] Step 4:

[0280] The server runs a voice synthesis model such as WaveNet to combine the voice features and the music information selected by the user. As a result, voice information matching the melody line of the music is output.

[0281] Step 5:

[0282] The server integrates the voice and visual materials using FFmpeg, a video generation tool, based on the generated voice information. In this step, supplementary information such as background music and animation is used to create a visually appealing video.

[0283] Step 6:

[0284] The server returns the completed music video data to the terminal, and the terminal receives this and makes it available for the user to view. This video is played within the application on the terminal, and the user can enjoy the content.

[0285] Step 7:

[0286] The user can transmit the generated video via social media or a messaging platform using the sharing function of the application. This enables wide sharing of the generated content.

[0287] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0288] This invention realizes a system that provides more personalized music videos by recognizing emotions from the user's voice data and reflecting them in the selected music and generated content. In addition to voice synthesis means, video generation means, and distribution means, this system utilizes an emotion engine that analyzes the user's emotions in real time and optimizes the content based on that analysis.

[0289] First, the user records their voice via a device and uploads this audio data to the system. At the same time, the user selects a song of their choice from the music library. This audio data is sent to a server, which uses an emotion engine to identify emotions from the user's voice. For example, if the server recognizes that the user's voice contains the emotion of "joy," it uses this information to generate audio data that reflects that emotion using speech synthesis.

[0290] Next, the server adjusts the tempo of the music and the selection of instruments based on the emotional information obtained from the emotion engine, and also modifies the colors and effects in the video content. This process generates a music video that matches the user's emotions. For example, if the system recognizes that the user is feeling "sadness," the music will become calmer, and the visuals will be updated with more subdued colors to match.

[0291] The generated music video is encoded on the server and sent to the device. Users can then view it on their device and share it on social media, etc. This system allows users to easily enjoy more personalized music based on their individual emotions.

[0292] The following describes the processing flow.

[0293] Step 1:

[0294] The user records their own voice and saves this audio data to their device. Then, the user uploads the recorded audio from their device to the system.

[0295] Step 2:

[0296] The user selects their preferred song from the music library provided by the system. The selected song information is sent from the terminal to the server.

[0297] Step 3:

[0298] The server uses an emotion engine to analyze audio features such as pitch, rhythm, and timbre on the audio data received from the user, and also recognizes the user's emotions from the audio.

[0299] Step 4:

[0300] The server performs speech synthesis necessary for generating music videos based on the recognized emotion information. It adjusts the tempo and melody of the music and applies effects according to the target emotion.

[0301] Step 5:

[0302] The server adds background music to the data obtained through speech synthesis and processes the visual content to resonate with the user's emotions. As a result, colors and visual effects corresponding to emotions are reflected in the music video.

[0303] Step 6:

[0304] The server encodes the generated music video and prepares it for distribution in a format playable on the user's device.

[0305] Step 7:

[0306] The terminal receives the music video distributed from the server and displays it in a form that can be immediately viewed by the user. After watching the video, the user can share it on SNS or the like as needed to spread their emotional expressions.

[0307] (Example 2)

[0308] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] In the prior art, it was difficult to easily generate individualized media content that reflects the emotions of the user. In particular, it was impossible to analyze the actual emotions of the user through voice and realize a consistent harmony of music and video based on this. This has been a major obstacle to improving the user experience.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0311] In this invention, the server includes an analysis means for identifying emotions from the user's voice, a voice synthesis means for generating voice data in combination with music data, and a generation means for adjusting and generating music characteristics and visual characteristics. Thereby, it becomes possible to automatically generate individualized music videos according to the emotions of the user and improve the user experience.

[0312] The "user" is the entity that inputs voice using the system and generates individualized media content.}

[0313] The "analysis means for identifying emotions" is a technology that analyzes the user's voice and has the function of specifying the emotions contained in the voice.

[0314] ] The "voice synthesis means" is a technology that integrates with other music data based on the analyzed emotion information and generates new voice data.

[0315] "Generation means" refers to a technology that uses data obtained from speech synthesis means to adjust and integrate music and visual characteristics to create media content.

[0316] "Distribution means" refers to technology that has the function of transmitting generated media content to a user's communication device.

[0317] A "data collection" is a database containing multiple existing songs that users can select from.

[0318] "Voice adjustment means" refers to technology that automatically adjusts the pitch and timing of voice data to match the user's emotional information.

[0319] This system identifies emotions through a user's voice and generates personalized media content based on those emotions. Users first record audio data using their own devices and upload it to the system. During this process, users can also select their preferred music from the data set. The server receives the uploaded audio data and uses analysis tools to identify emotions. These analysis tools utilize speech machine learning algorithms and natural language processing techniques.

[0320] Based on the analyzed emotional information, the server uses speech synthesis to integrate music and audio data that correspond to the user's emotions, generating new audio output. A generative AI model is used in this process. Next, the generative means adjusts characteristics such as the tempo of the music and the color tone of the visuals to match the emotions, completing the final media content. This media content is delivered to the user's device, and the user can view or share the content.

[0321] For example, if a user provides audio expressing a desire to relax, the system will analyze the audio and generate a video that combines relaxing music with calming visuals. Another example of a prompt to input to the generation AI model would be, "Express your desire to relax in audio and generate a video with calming music and simple visuals."

[0322] These features are implemented by their respective hardware and software components, aiming to provide users with new music and visual experiences.

[0323] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0324] Step 1:

[0325] The user records audio data using their device. The audio recorded by the user includes elements that express specific emotions. This audio data is saved as a digital file on the device and stored in a temporary cache. The input data is raw audio data, and the result is an audio file ready to be sent to the server as output.

[0326] Step 2:

[0327] The user uploads audio data recorded via their device to the server. Simultaneously, the user selects a preferred song from the system's data collection. The selected song is also sent to the server. The input consists of the audio file and the selected song information, while the output is the status of the audio data's reception on the server.

[0328] Step 3:

[0329] The server receives the uploaded audio data and begins processing it with an analysis tool that identifies emotions. The analysis tool uses an audio machine learning algorithm to extract features from the audio data (such as tone, pitch, and tempo) and identify the user's emotions. The input is the audio data, and the output is the identified emotion information.

[0330] Step 4:

[0331] The server uses speech synthesis to integrate the identified emotion information with the selected song. This generates new voice data that corresponds to the emotion. A generative AI model is used in this process to create voice output that reflects the emotion. The input is emotion information and song data, and the output is the integrated voice data.

[0332] Step 5:

[0333] The server uses a generation mechanism to adjust the music and visual characteristics based on the audio data created in the previous step, generating the final media content. The tempo of the music and the color tones of the visuals are adjusted to match the identified emotion. The input is integrated audio data, and the output is the completed media content.

[0334] Step 6:

[0335] The server encodes the generated media content and delivers it to the user's terminal. During encoding, the optimal format and compression method are selected to ensure efficient transfer. The input is media content, and the output is a media file viewable on the user's terminal.

[0336] Step 7:

[0337] Users view media content received on their devices. After viewing, if they like the content, they can share it via social media, etc. The input is the media file received by the user, and the output is the experience of playing the content.

[0338] (Application Example 2)

[0339] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0340] The challenge is to create a system that generates content reflecting individual emotions based on the user's voice data, allowing them to enjoy a more personalized music experience.

[0341] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0342] In this invention, the server includes an emotion engine means that analyzes emotions from a user's voice data and generates personalized existing music data and video data selected based on that emotion data; a content generation means that generates integrated music and visual content using the voice data and video data that reflect the emotion information generated by the emotion engine means; and a communication means for distributing the integrated content to a communication terminal. This enables users to view and share personalized music videos that are tailored to their emotions.

[0343] "Audio data" is a collection of acoustic signals generated by a user's speech or voice.

[0344] An "emotion engine means" is a system or device for analyzing voice data to identify the user's emotions and generating data based on the identification results.

[0345] A "content generation method" is a system or device that generates new media by integrating music and visual elements based on emotional information.

[0346] "Communication means" refers to a system or device for transmitting generated digital content to another device via a network.

[0347] A "communication terminal" is a device used by users to receive and display digital content, and includes smartphones and tablets.

[0348] To realize this invention, the system first involves the user performing voice input using the terminal's microphone. The terminal uploads the recorded voice data to a server. The server analyzes the emotions from the voice data using an emotion engine and digitizes the results. This analysis uses speech recognition software (e.g., IBM Watson Tone Analyzer). Based on the analyzed emotion information, a content generation means generates personalized content incorporating music and visual elements. This generation process utilizes video editing software APIs (e.g., Adobe Premiere Pro API). Finally, the generated content is sent from the server to the communication terminal, making it available for the user to view. Internet connectivity is used for this communication.

[0349] For example, if a user says "I'm feeling great today," the server's emotion engine identifies this as "joy" and generates a music video combining upbeat music and cheerful visuals.

[0350] Examples of prompts for a generative AI model include the following:

[0351] "When a user is experiencing feelings of joy, generate music and visuals that match those feelings. The music should be upbeat, and the visuals should use bright colors."

[0352] In this way, users can enjoy personalized content that matches their own emotions.

[0353] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0354] Step 1:

[0355] The user inputs voice using the device. The device records the user's voice using its built-in microphone. This recorded data is saved as a digital audio file. As a result, the audio data becomes the input.

[0356] Step 2:

[0357] The terminal uploads the recorded audio data to the server. Here, the audio data is transferred to the server via a communication protocol between devices. The audio data is stored on the server and becomes the input for the next calculation process.

[0358] Step 3:

[0359] The server uses an emotion engine to analyze voice data and identify the user's emotions. A speech recognition API (e.g., IBM Watson Tone Analyzer) is used to identify emotions by analyzing the pitch and tone of the voice from the input voice data. Emotion labels (e.g., joy, sadness) are generated as output.

[0360] Step 4:

[0361] The server utilizes the acquired emotion data to provide emotional information to the content generation engine. The engine references video data and music libraries to select music and visual effects that match the emotion. Digital content is created using a content generation API (e.g., Adobe Premiere Pro API). As output, a personalized music video based on the specific emotion is generated.

[0362] Step 5:

[0363] The server encodes the generated content and streams it to the user's communication device. The encoded data enables efficient data transfer and supports smooth playback on the device. The user can complete the experience by viewing this content. Once the digital content is sent to the device, its output is provided visually.

[0364] This process allows users to receive and enjoy personalized content that reflects their own emotions.

[0365] 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.

[0366] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0367] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0368] [Third Embodiment]

[0369] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0370] 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.

[0371] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0372] 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.

[0373] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0374] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0375] 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.

[0376] 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.

[0377] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0378] The 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.

[0379] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0380] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0381] This invention provides a system that enables users to efficiently generate high-quality music videos using individual audio data. This system is mainly composed of a combination of speech synthesis means, video generation means, and distribution means.

[0382] First, the user records audio data on their device via a dedicated application or web platform and uploads it to the system. At the same time, the user can select existing music data from a provided library. The device then sends this data to the server.

[0383] The server analyzes the features of the user's voice and prepares it to be combined with selected music data. This process involves using speech synthesis technology to match the user's voice to the melody line of the selected song. Specifically, the server matches the user's recorded voice to an existing pop song, generating audio that sounds as if the user is professionally singing the song.

[0384] In the video generation phase, the server adds existing background music to the generated audio and integrates appropriate visual content. This process generates the completed music video. The terminal receives the generated music video from the server and provides it to the user in a viewable format.

[0385] Users can not only enjoy these music videos themselves, but also share them using platforms such as social media. This system allows users to easily create their own musical works without having to worry about complicated procedures or high costs.

[0386] The following describes the processing flow.

[0387] Step 1:

[0388] Users record their voices using a dedicated application or web platform and save them as audio data files. They then upload this audio data from their device to the system.

[0389] Step 2:

[0390] The user selects an existing song they want to use from the music library provided within the system. The selected song information is sent to the server via the terminal.

[0391] Step 3:

[0392] The server analyzes the audio data received from the user and extracts audio features such as pitch, timing, and timbre. This prepares the basic data needed to determine the compatibility with the selected music data.

[0393] Step 4:

[0394] Based on the analyzed speech features, the server uses speech synthesis technology to generate audio data that matches the user's voice to the melody line of the selected song. At this stage, audio adjustments and effects are also applied.

[0395] Step 5:

[0396] The server combines the generated audio data with existing background music and adds visual content to create a music video. This visual content includes lyrics, theme-specific images, and video clips.

[0397] Step 6:

[0398] The server encodes the generated music video and converts it into a format that can be sent to the user's device.

[0399] Step 7:

[0400] The device receives music videos sent from the server and displays them to the user in a viewable format. Users can not only watch these videos but also share them on social media and other platforms.

[0401] (Example 1)

[0402] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0403] Modern users want to easily and efficiently generate high-quality music content using their individual voices. However, existing technologies require advanced expertise and high costs, making them inaccessible to individuals. Furthermore, the complexity of improving sound quality and integrating visual elements makes it difficult for users to create content they are satisfied with.

[0404] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0405] In this invention, the server includes a generation means that analyzes voice information input by the user and generates voice information by combining it with existing music data selected based on that analysis; a synthesis means that uses the voice information generated by the generation means to generate music content that integrates background sounds and visual information; and a supply means for supplying the music content to the user's device. This enables the user to generate and listen to high-quality music content without experiencing complex procedures or technical hurdles.

[0406] "Voice information" refers to the voice data entered by the user, and its features are the subject of analysis.

[0407] "Generation means" refers to processing means for generating synthesized speech by combining analyzed speech information with existing music data.

[0408] A "synthesis method" is a means that integrates background sounds and visual information into the generated audio to complete the music content.

[0409] "Supply means" refers to processing means that provide completed music content to the user's device and make it available for listening.

[0410] A "collection" refers to a library of existing music data that users can select, offering a variety of choices.

[0411] "Adjustment means" refers to processing means that have the function of automatically adjusting the pitch and temporal arrangement of the user's voice information to match the music data.

[0412] This system is a platform for users to generate music content using their own voice. First, users record voice information using a dedicated application or web platform and upload it from their device to the server along with selected existing music data. Here, users can select from a large number of music files from their library.

[0413] The server analyzes the received audio information and extracts its features (such as pitch and tempo). This analysis utilizes speech analysis technology powered by a generative AI model. Subsequently, the server generates audio information by matching the analyzed audio information to the melody line of the selected music data. This generation process is carried out by an audio adjustment mechanism that automatically adjusts the pitch and temporal placement of sounds. An example of a prompt message is an instruction such as, "Record user voice and combine it with the selected song to generate high-quality music."

[0414] Next, the server integrates the generated audio information with visual information and background sounds to form music content. At this time, the visual information is dynamically changed according to the emotion and tempo of the audio, resulting in the creation of high-quality music content.

[0415] The device receives the completed music content from the server and provides it to the user. The user can not only enjoy this content personally, but also share it with others via an online platform.

[0416] This system allows users to easily and efficiently create their own music content, even without specialized skills.

[0417] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0418] Step 1:

[0419] The user records audio using a dedicated application or web platform. The recorded data is saved to the device along with selected existing music data. This process provides an interface for the user to select music data from their library along with their own audio. The input is the user's audio data and the selected music data, and the output is a combination of these data.

[0420] Step 2:

[0421] The device sends the audio data recorded by the user and the selected music data to the server. This prepares the server for data processing. The input is the audio and music data stored on the device, and the output is the data sent to the server.

[0422] Step 3:

[0423] The server receives the transmitted audio data and analyzes its features. A generative AI model is used to extract the pitch, tempo, and voice quality of the audio data. The result of the analysis is the structural features of this audio data. The input is the audio data received by the server, and the output is the analyzed audio features.

[0424] Step 4:

[0425] The server integrates the voice with selected music data based on the features of the analyzed voice data. During this process, voice adjustment mechanisms are used to generate voice that matches the user's voice to the music's melody. Specifically, the pitch and timing of the voice are automatically adjusted. The input consists of voice features and selected music data, and the output is the integrated voice data.

[0426] Step 5:

[0427] The server uses the generated audio to create music content that integrates visual information and background sounds. The visual information is dynamically selected based on the emotion and tempo of the audio data. The input is integrated audio data, and the output is the completed music content.

[0428] Step 6:

[0429] The device receives completed music content from the server and provides it to the user. The user can listen to this content and share it on platforms such as social media as needed. The input is music content from the server, and the output is content converted into a format viewable by the user.

[0430] (Application Example 1)

[0431] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0432] There is a lack of a platform that allows users to efficiently create high-quality music videos using their own voices and easily share them. Traditional methods require high levels of expertise and cost for voice synthesis and video generation, making them inaccessible to the average user. Furthermore, they lack features for smoothly sharing the generated content.

[0433] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0434] In this invention, the server includes a speech synthesis means that analyzes audio features input by the user and generates audio information by combining them with selected music information; a video generation means that uses the audio information generated by the speech synthesis means to integrate supplementary information and visual information to generate video information; and a distribution means for distributing the video information to an end-user device. This enables users to create and share professional music videos without requiring specialized knowledge or incurring high costs.

[0435] "Speech features" are characteristic elements extracted from speech data, and include information such as pitch, intensity, and voice quality.

[0436] "Song information" refers to data related to music, which may include melody, rhythm, and lyrics.

[0437] "Audio information" refers to data generated based on audio features, and specifically to synthesized data produced through speech synthesis.

[0438] "Speech synthesis means" refers to a process and apparatus for generating speech information based on speech features and music information.

[0439] "Supplemental information" refers to background music or sound effects added to enhance or supplement audio information.

[0440] "Visual information" refers to visual content such as images, videos, and animations used to constitute video information.

[0441] "Video generation means" refers to a process and apparatus for generating video information by combining audio information, supplementary information, and visual information.

[0442] "End-user device" refers to a device used by a user to view or interact with the final generated content, and includes smartphones and tablets.

[0443] "Distribution means" refers to the process and equipment for transmitting generated video information to end-user devices.

[0444] To implement this invention, the user operates a dedicated application using their smartphone or tablet. First, the user activates an interface for recording voice on their smartphone and records their voice. Once recording is complete, the application sends the voice data to a server in the cloud. The server has voice processing libraries such as Google Cloud Speech-to-Text and WaveNet installed, which analyze the user's voice features and combine them with selected music information. Based on the resulting voice information, supplementary and visual information is integrated, and a video is generated using tools such as FFmpeg.

[0445] The generated video is transmitted to the end-user's device using a distribution method, and the user can view it or share it on social media. Specifically, for example, a user can create a professional video of themselves covering a hit song with their own voice and share it with friends for enjoyment. An example of a prompt message in this case would be: "Synthesize the audio files recorded by the user to create a professional soundtrack set to the song 'XYZ Song,' add visual effects, and generate a video."

[0446] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0447] Step 1:

[0448] The user launches an application on their smartphone and uses the voice recording function to record their voice. At this stage, the user's voice is saved on the device as an audio data file.

[0449] Step 2:

[0450] The device sends the recorded audio data to a server located in the cloud. To ensure security, the data is encrypted and stored on the server as audio data.

[0451] Step 3:

[0452] The server uses the Google Cloud Speech-to-Text service as input to analyze the audio features of the received audio data. As a result, it outputs feature data including the pitch and tempo of the audio.

[0453] Step 4:

[0454] The server runs a speech synthesis model such as WaveNet to combine speech features with user-selected song information. This results in the output of speech information that matches the melody line of the song.

[0455] Step 5:

[0456] The server uses the generated audio information to integrate the audio and visual elements using the video generation tool FFmpeg. In this step, supplementary information such as background music and animation is used to create a visually appealing video.

[0457] Step 6:

[0458] The server sends the completed music video data back to the device, which receives it and makes it available for the user to view. The video plays within the device's application, allowing the user to enjoy the content.

[0459] Step 7:

[0460] Users can send videos generated using the application's sharing function via social media and messaging platforms. This enables widespread sharing of the generated content.

[0461] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0462] This invention realizes a system that provides more personalized music videos by recognizing emotions from the user's voice data and reflecting them in the selected music and generated content. In addition to voice synthesis means, video generation means, and distribution means, this system utilizes an emotion engine that analyzes the user's emotions in real time and optimizes the content based on that analysis.

[0463] First, the user records their voice via a device and uploads this audio data to the system. At the same time, the user selects a song of their choice from the music library. This audio data is sent to a server, which uses an emotion engine to identify emotions from the user's voice. For example, if the server recognizes that the user's voice contains the emotion of "joy," it uses this information to generate audio data that reflects that emotion using speech synthesis.

[0464] Next, the server adjusts the tempo of the music and the selection of instruments based on the emotional information obtained from the emotion engine, and also modifies the colors and effects in the video content. This process generates a music video that matches the user's emotions. For example, if the system recognizes that the user is feeling "sadness," the music will become calmer, and the visuals will be updated with more subdued colors to match.

[0465] The generated music video is encoded on the server and sent to the device. Users can then view it on their device and share it on social media, etc. This system allows users to easily enjoy more personalized music based on their individual emotions.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] The user records their own voice and saves this audio data to their device. Then, the user uploads the recorded audio from their device to the system.

[0469] Step 2:

[0470] The user selects their preferred song from the music library provided by the system. The selected song information is sent from the terminal to the server.

[0471] Step 3:

[0472] The server uses an emotion engine to analyze audio features such as pitch, rhythm, and timbre on the audio data received from the user, and also recognizes the user's emotions from the audio.

[0473] Step 4:

[0474] The server performs speech synthesis necessary for generating music videos based on the recognized emotion information. It adjusts the tempo and melody of the music and applies effects according to the target emotion.

[0475] Step 5:

[0476] The server adds background music to the data obtained through speech synthesis and processes the visual content to resonate with the user's emotions. As a result, colors and visual effects corresponding to emotions are reflected in the music video.

[0477] Step 6:

[0478] The server encodes the generated music video and prepares it for distribution in a format playable on the user's device.

[0479] Step 7:

[0480] The device receives music videos streamed from the server and displays them to the user in an instantly viewable format. After watching the videos, users can share them on social media or other platforms as needed to spread their emotional expression.

[0481] (Example 2)

[0482] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0483] Conventional technologies have made it difficult to easily generate personalized media content that reflects user emotions. In particular, it has been impossible to analyze a user's actual emotions through voice and achieve consistent harmony of music and visuals based on these emotions. This has been a major obstacle to improving the user experience.

[0484] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0485] In this invention, the server includes an analysis means for identifying emotions from the user's speech, a speech synthesis means for generating audio data by combining it with music data, and a generation means for adjusting and generating music and visual characteristics. This makes it possible to automatically generate personalized music videos that respond to the user's emotions, thereby improving the user experience.

[0486] A "user" is an entity that uses a system to input voice and generate personalized media content.

[0487] "An analytical means for identifying emotions" refers to a technology that analyzes a user's voice and identifies the emotions contained within that voice.

[0488] "Speech synthesis means" is a technology that generates new speech data by integrating analyzed emotional information with other music data.

[0489] "Generation means" refers to a technology that uses data obtained from speech synthesis means to adjust and integrate music and visual characteristics to create media content.

[0490] "Distribution means" refers to technology that has the function of transmitting generated media content to a user's communication device.

[0491] A "data collection" is a database containing multiple existing songs that users can select from.

[0492] "Voice adjustment means" refers to technology that automatically adjusts the pitch and timing of voice data to match the user's emotional information.

[0493] This system identifies emotions through a user's voice and generates personalized media content based on those emotions. Users first record audio data using their own devices and upload it to the system. During this process, users can also select their preferred music from the data set. The server receives the uploaded audio data and uses analysis tools to identify emotions. These analysis tools utilize speech machine learning algorithms and natural language processing techniques.

[0494] Based on the analyzed emotional information, the server uses speech synthesis to integrate music and audio data that correspond to the user's emotions, generating new audio output. A generative AI model is used in this process. Next, the generative means adjusts characteristics such as the tempo of the music and the color tone of the visuals to match the emotions, completing the final media content. This media content is delivered to the user's device, and the user can view or share the content.

[0495] For example, if a user provides audio expressing a desire to relax, the system will analyze the audio and generate a video that combines relaxing music with calming visuals. Another example of a prompt to input to the generation AI model would be, "Express your desire to relax in audio and generate a video with calming music and simple visuals."

[0496] These features are implemented by their respective hardware and software components, aiming to provide users with new music and visual experiences.

[0497] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0498] Step 1:

[0499] The user records audio data using their device. The audio recorded by the user includes elements that express specific emotions. This audio data is saved as a digital file on the device and stored in a temporary cache. The input data is raw audio data, and the result is an audio file ready to be sent to the server as output.

[0500] Step 2:

[0501] The user uploads audio data recorded via their device to the server. Simultaneously, the user selects a preferred song from the system's data collection. The selected song is also sent to the server. The input consists of the audio file and the selected song information, while the output is the status of the audio data's reception on the server.

[0502] Step 3:

[0503] The server receives the uploaded audio data and begins processing it with an analysis tool that identifies emotions. The analysis tool uses an audio machine learning algorithm to extract features from the audio data (such as tone, pitch, and tempo) and identify the user's emotions. The input is the audio data, and the output is the identified emotion information.

[0504] Step 4:

[0505] The server uses speech synthesis to integrate the identified emotion information with the selected song. This generates new voice data that corresponds to the emotion. A generative AI model is used in this process to create voice output that reflects the emotion. The input is emotion information and song data, and the output is the integrated voice data.

[0506] Step 5:

[0507] The server uses a generation mechanism to adjust the music and visual characteristics based on the audio data created in the previous step, generating the final media content. The tempo of the music and the color tones of the visuals are adjusted to match the identified emotion. The input is integrated audio data, and the output is the completed media content.

[0508] Step 6:

[0509] The server encodes the generated media content and delivers it to the user's terminal. During encoding, the optimal format and compression method are selected to ensure efficient transfer. The input is media content, and the output is a media file viewable on the user's terminal.

[0510] Step 7:

[0511] Users view media content received on their devices. After viewing, if they like the content, they can share it via social media, etc. The input is the media file received by the user, and the output is the experience of playing the content.

[0512] (Application Example 2)

[0513] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] The challenge is to create a system that generates content reflecting individual emotions based on the user's voice data, allowing them to enjoy a more personalized music experience.

[0515] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0516] In this invention, the server includes an emotion engine means that analyzes emotions from a user's voice data and generates personalized existing music data and video data selected based on that emotion data; a content generation means that generates integrated music and visual content using the voice data and video data that reflect the emotion information generated by the emotion engine means; and a communication means for distributing the integrated content to a communication terminal. This enables users to view and share personalized music videos that are tailored to their emotions.

[0517] "Audio data" is a collection of acoustic signals generated by a user's speech or voice.

[0518] An "emotion engine means" is a system or device for analyzing voice data to identify the user's emotions and generating data based on the identification results.

[0519] A "content generation method" is a system or device that generates new media by integrating music and visual elements based on emotional information.

[0520] "Communication means" refers to a system or device for transmitting generated digital content to another device via a network.

[0521] A "communication terminal" is a device used by users to receive and display digital content, and includes smartphones and tablets.

[0522] To realize this invention, the system first involves the user performing voice input using the terminal's microphone. The terminal uploads the recorded voice data to a server. The server analyzes the emotions from the voice data using an emotion engine and digitizes the results. This analysis uses speech recognition software (e.g., IBM Watson Tone Analyzer). Based on the analyzed emotion information, a content generation means generates personalized content incorporating music and visual elements. This generation process utilizes video editing software APIs (e.g., Adobe Premiere Pro API). Finally, the generated content is sent from the server to the communication terminal, making it available for the user to view. Internet connectivity is used for this communication.

[0523] For example, if a user says "I'm feeling great today," the server's emotion engine identifies this as "joy" and generates a music video combining upbeat music and cheerful visuals.

[0524] Examples of prompts for a generative AI model include the following:

[0525] "When a user is experiencing feelings of joy, generate music and visuals that match those feelings. The music should be upbeat, and the visuals should use bright colors."

[0526] In this way, users can enjoy personalized content that matches their own emotions.

[0527] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0528] Step 1:

[0529] The user inputs voice using the device. The device records the user's voice using its built-in microphone. This recorded data is saved as a digital audio file. As a result, the audio data becomes the input.

[0530] Step 2:

[0531] The terminal uploads the recorded audio data to the server. Here, the audio data is transferred to the server via a communication protocol between devices. The audio data is stored on the server and becomes the input for the next calculation process.

[0532] Step 3:

[0533] The server uses an emotion engine to analyze voice data and identify the user's emotions. A speech recognition API (e.g., IBM Watson Tone Analyzer) is used to identify emotions by analyzing the pitch and tone of the voice from the input voice data. Emotion labels (e.g., joy, sadness) are generated as output.

[0534] Step 4:

[0535] The server utilizes the acquired emotion data to provide emotional information to the content generation engine. The engine references video data and music libraries to select music and visual effects that match the emotion. Digital content is created using a content generation API (e.g., Adobe Premiere Pro API). As output, a personalized music video based on the specific emotion is generated.

[0536] Step 5:

[0537] The server encodes the generated content and streams it to the user's communication device. The encoded data enables efficient data transfer and supports smooth playback on the device. The user can complete the experience by viewing this content. Once the digital content is sent to the device, its output is provided visually.

[0538] This process allows users to receive and enjoy personalized content that reflects their own emotions.

[0539] 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.

[0540] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0541] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0542] [Fourth Embodiment]

[0543] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0544] 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.

[0545] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0546] 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.

[0547] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0548] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0549] 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.

[0550] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0551] 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.

[0552] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0553] The 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.

[0554] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0555] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0556] This invention provides a system that enables users to efficiently generate high-quality music videos using individual audio data. This system is mainly composed of a combination of speech synthesis means, video generation means, and distribution means.

[0557] First, the user records audio data on their device via a dedicated application or web platform and uploads it to the system. At the same time, the user can select existing music data from a provided library. The device then sends this data to the server.

[0558] The server analyzes the features of the user's voice and prepares it to be combined with selected music data. This process involves using speech synthesis technology to match the user's voice to the melody line of the selected song. Specifically, the server matches the user's recorded voice to an existing pop song, generating audio that sounds as if the user is professionally singing the song.

[0559] In the video generation phase, the server adds existing background music to the generated audio and integrates appropriate visual content. This process generates the completed music video. The terminal receives the generated music video from the server and provides it to the user in a viewable format.

[0560] Users can not only enjoy these music videos themselves, but also share them using platforms such as social media. This system allows users to easily create their own musical works without having to worry about complicated procedures or high costs.

[0561] The following describes the processing flow.

[0562] Step 1:

[0563] Users record their voices using a dedicated application or web platform and save them as audio data files. They then upload this audio data from their device to the system.

[0564] Step 2:

[0565] The user selects an existing song they want to use from the music library provided within the system. The selected song information is sent to the server via the terminal.

[0566] Step 3:

[0567] The server analyzes the audio data received from the user and extracts audio features such as pitch, timing, and timbre. This prepares the basic data needed to determine the compatibility with the selected music data.

[0568] Step 4:

[0569] Based on the analyzed speech features, the server uses speech synthesis technology to generate audio data that matches the user's voice to the melody line of the selected song. At this stage, audio adjustments and effects are also applied.

[0570] Step 5:

[0571] The server combines the generated audio data with existing background music and adds visual content to create a music video. This visual content includes lyrics, theme-specific images, and video clips.

[0572] Step 6:

[0573] The server encodes the generated music video and converts it into a format that can be sent to the user's device.

[0574] Step 7:

[0575] The device receives music videos sent from the server and displays them to the user in a viewable format. Users can not only watch these videos but also share them on social media and other platforms.

[0576] (Example 1)

[0577] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0578] Modern users want to easily and efficiently generate high-quality music content using their individual voices. However, existing technologies require advanced expertise and high costs, making them inaccessible to individuals. Furthermore, the complexity of improving sound quality and integrating visual elements makes it difficult for users to create content they are satisfied with.

[0579] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0580] In this invention, the server includes a generation means that analyzes voice information input by the user and generates voice information by combining it with existing music data selected based on that analysis; a synthesis means that uses the voice information generated by the generation means to generate music content that integrates background sounds and visual information; and a supply means for supplying the music content to the user's device. This enables the user to generate and listen to high-quality music content without experiencing complex procedures or technical hurdles.

[0581] "Voice information" refers to the voice data entered by the user, and its features are the subject of analysis.

[0582] "Generation means" refers to processing means for generating synthesized speech by combining analyzed speech information with existing music data.

[0583] A "synthesis method" is a means that integrates background sounds and visual information into the generated audio to complete the music content.

[0584] "Supply means" refers to processing means that provide completed music content to the user's device and make it available for listening.

[0585] A "collection" refers to a library of existing music data that users can select, offering a variety of choices.

[0586] "Adjustment means" refers to processing means that have the function of automatically adjusting the pitch and temporal arrangement of the user's voice information to match the music data.

[0587] This system is a platform for users to generate music content using their own voice. First, users record voice information using a dedicated application or web platform and upload it from their device to the server along with selected existing music data. Here, users can select from a large number of music files from their library.

[0588] The server analyzes the received audio information and extracts its features (such as pitch and tempo). This analysis utilizes speech analysis technology powered by a generative AI model. Subsequently, the server generates audio information by matching the analyzed audio information to the melody line of the selected music data. This generation process is carried out by an audio adjustment mechanism that automatically adjusts the pitch and temporal placement of sounds. An example of a prompt message is an instruction such as, "Record user voice and combine it with the selected song to generate high-quality music."

[0589] Next, the server integrates the generated audio information with visual information and background sounds to form music content. At this time, the visual information is dynamically changed according to the emotion and tempo of the audio, resulting in the creation of high-quality music content.

[0590] The device receives the completed music content from the server and provides it to the user. The user can not only enjoy this content personally, but also share it with others via an online platform.

[0591] This system allows users to easily and efficiently create their own music content, even without specialized skills.

[0592] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0593] Step 1:

[0594] The user records audio using a dedicated application or web platform. The recorded data is saved to the device along with selected existing music data. This process provides an interface for the user to select music data from their library along with their own audio. The input is the user's audio data and the selected music data, and the output is a combination of these data.

[0595] Step 2:

[0596] The device sends the audio data recorded by the user and the selected music data to the server. This prepares the server for data processing. The input is the audio and music data stored on the device, and the output is the data sent to the server.

[0597] Step 3:

[0598] The server receives the transmitted audio data and analyzes its features. A generative AI model is used to extract the pitch, tempo, and voice quality of the audio data. The result of the analysis is the structural features of this audio data. The input is the audio data received by the server, and the output is the analyzed audio features.

[0599] Step 4:

[0600] The server integrates the voice with selected music data based on the features of the analyzed voice data. During this process, voice adjustment mechanisms are used to generate voice that matches the user's voice to the music's melody. Specifically, the pitch and timing of the voice are automatically adjusted. The input consists of voice features and selected music data, and the output is the integrated voice data.

[0601] Step 5:

[0602] The server uses the generated audio to create music content that integrates visual information and background sounds. The visual information is dynamically selected based on the emotion and tempo of the audio data. The input is integrated audio data, and the output is the completed music content.

[0603] Step 6:

[0604] The device receives completed music content from the server and provides it to the user. The user can listen to this content and share it on platforms such as social media as needed. The input is music content from the server, and the output is content converted into a format viewable by the user.

[0605] (Application Example 1)

[0606] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0607] There is a lack of a platform that allows users to efficiently create high-quality music videos using their own voices and easily share them. Traditional methods require high levels of expertise and cost for voice synthesis and video generation, making them inaccessible to the average user. Furthermore, they lack features for smoothly sharing the generated content.

[0608] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0609] In this invention, the server includes a speech synthesis means that analyzes audio features input by the user and generates audio information by combining them with selected music information; a video generation means that uses the audio information generated by the speech synthesis means to integrate supplementary information and visual information to generate video information; and a distribution means for distributing the video information to an end-user device. This enables users to create and share professional music videos without requiring specialized knowledge or incurring high costs.

[0610] "Speech features" are characteristic elements extracted from speech data, and include information such as pitch, intensity, and voice quality.

[0611] "Song information" refers to data related to music, which may include melody, rhythm, and lyrics.

[0612] "Audio information" refers to data generated based on audio features, and specifically to synthesized data produced through speech synthesis.

[0613] "Speech synthesis means" refers to a process and apparatus for generating speech information based on speech features and music information.

[0614] "Supplemental information" refers to background music or sound effects added to enhance or supplement audio information.

[0615] "Visual information" refers to visual content such as images, videos, and animations used to constitute video information.

[0616] "Video generation means" refers to a process and apparatus for generating video information by combining audio information, supplementary information, and visual information.

[0617] "End-user device" refers to a device used by a user to view or interact with the final generated content, and includes smartphones and tablets.

[0618] "Distribution means" refers to the process and equipment for transmitting generated video information to end-user devices.

[0619] To implement this invention, the user operates a dedicated application using their smartphone or tablet. First, the user activates an interface for recording voice on their smartphone and records their voice. Once recording is complete, the application sends the voice data to a server in the cloud. The server has voice processing libraries such as Google Cloud Speech-to-Text and WaveNet installed, which analyze the user's voice features and combine them with selected music information. Based on the resulting voice information, supplementary and visual information is integrated, and a video is generated using tools such as FFmpeg.

[0620] The generated video is transmitted to the end-user's device using a distribution method, and the user can view it or share it on social media. Specifically, for example, a user can create a professional video of themselves covering a hit song with their own voice and share it with friends for enjoyment. An example of a prompt message in this case would be: "Synthesize the audio files recorded by the user to create a professional soundtrack set to the song 'XYZ Song,' add visual effects, and generate a video."

[0621] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0622] Step 1:

[0623] The user launches an application on their smartphone and uses the voice recording function to record their voice. At this stage, the user's voice is saved on the device as an audio data file.

[0624] Step 2:

[0625] The device sends the recorded audio data to a server located in the cloud. To ensure security, the data is encrypted and stored on the server as audio data.

[0626] Step 3:

[0627] The server uses the Google Cloud Speech-to-Text service as input to analyze the audio features of the received audio data. As a result, it outputs feature data including the pitch and tempo of the audio.

[0628] Step 4:

[0629] The server runs a speech synthesis model such as WaveNet to combine speech features with user-selected song information. This results in the output of speech information that matches the melody line of the song.

[0630] Step 5:

[0631] The server uses the generated audio information to integrate the audio and visual elements using the video generation tool FFmpeg. In this step, supplementary information such as background music and animation is used to create a visually appealing video.

[0632] Step 6:

[0633] The server sends the completed music video data back to the device, which receives it and makes it available for the user to view. The video plays within the device's application, allowing the user to enjoy the content.

[0634] Step 7:

[0635] Users can send videos generated using the application's sharing function via social media and messaging platforms. This enables widespread sharing of the generated content.

[0636] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0637] This invention realizes a system that provides more personalized music videos by recognizing emotions from the user's voice data and reflecting them in the selected music and generated content. In addition to voice synthesis means, video generation means, and distribution means, this system utilizes an emotion engine that analyzes the user's emotions in real time and optimizes the content based on that analysis.

[0638] First, the user records their voice via a device and uploads this audio data to the system. At the same time, the user selects a song of their choice from the music library. This audio data is sent to a server, which uses an emotion engine to identify emotions from the user's voice. For example, if the server recognizes that the user's voice contains the emotion of "joy," it uses this information to generate audio data that reflects that emotion using speech synthesis.

[0639] Next, the server adjusts the tempo of the music and the selection of instruments based on the emotional information obtained from the emotion engine, and also modifies the colors and effects in the video content. This process generates a music video that matches the user's emotions. For example, if the system recognizes that the user is feeling "sadness," the music will become calmer, and the visuals will be updated with more subdued colors to match.

[0640] The generated music video is encoded on the server and sent to the device. Users can then view it on their device and share it on social media, etc. This system allows users to easily enjoy more personalized music based on their individual emotions.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The user records their own voice and saves this audio data to their device. Then, the user uploads the recorded audio from their device to the system.

[0644] Step 2:

[0645] The user selects their preferred song from the music library provided by the system. The selected song information is sent from the terminal to the server.

[0646] Step 3:

[0647] The server uses an emotion engine to analyze audio features such as pitch, rhythm, and timbre on the audio data received from the user, and also recognizes the user's emotions from the audio.

[0648] Step 4:

[0649] The server performs speech synthesis necessary for generating music videos based on the recognized emotion information. It adjusts the tempo and melody of the music and applies effects according to the target emotion.

[0650] Step 5:

[0651] The server adds background music to the data obtained through speech synthesis and processes the visual content to resonate with the user's emotions. As a result, colors and visual effects corresponding to emotions are reflected in the music video.

[0652] Step 6:

[0653] The server encodes the generated music video and prepares it for distribution in a format playable on the user's device.

[0654] Step 7:

[0655] The device receives music videos streamed from the server and displays them to the user in an instantly viewable format. After watching the videos, users can share them on social media or other platforms as needed to spread their emotional expression.

[0656] (Example 2)

[0657] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] Conventional technologies have made it difficult to easily generate personalized media content that reflects user emotions. In particular, it has been impossible to analyze a user's actual emotions through voice and achieve consistent harmony of music and visuals based on these emotions. This has been a major obstacle to improving the user experience.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0660] In this invention, the server includes an analysis means for identifying emotions from the user's speech, a speech synthesis means for generating audio data by combining it with music data, and a generation means for adjusting and generating music and visual characteristics. This makes it possible to automatically generate personalized music videos that respond to the user's emotions, thereby improving the user experience.

[0661] A "user" is an entity that uses a system to input voice and generate personalized media content.

[0662] "An analytical means for identifying emotions" refers to a technology that analyzes a user's voice and identifies the emotions contained within that voice.

[0663] "Speech synthesis means" is a technology that generates new speech data by integrating analyzed emotional information with other music data.

[0664] "Generation means" refers to a technology that uses data obtained from speech synthesis means to adjust and integrate music and visual characteristics to create media content.

[0665] "Distribution means" refers to technology that has the function of transmitting generated media content to a user's communication device.

[0666] A "data collection" is a database containing multiple existing songs that users can select from.

[0667] "Voice adjustment means" refers to technology that automatically adjusts the pitch and timing of voice data to match the user's emotional information.

[0668] This system identifies emotions through a user's voice and generates personalized media content based on those emotions. Users first record audio data using their own devices and upload it to the system. During this process, users can also select their preferred music from the data set. The server receives the uploaded audio data and uses analysis tools to identify emotions. These analysis tools utilize speech machine learning algorithms and natural language processing techniques.

[0669] Based on the analyzed emotional information, the server uses speech synthesis to integrate music and audio data that correspond to the user's emotions, generating new audio output. A generative AI model is used in this process. Next, the generative means adjusts characteristics such as the tempo of the music and the color tone of the visuals to match the emotions, completing the final media content. This media content is delivered to the user's device, and the user can view or share the content.

[0670] For example, if a user provides audio expressing a desire to relax, the system will analyze the audio and generate a video that combines relaxing music with calming visuals. Another example of a prompt to input to the generation AI model would be, "Express your desire to relax in audio and generate a video with calming music and simple visuals."

[0671] These features are implemented by their respective hardware and software components, aiming to provide users with new music and visual experiences.

[0672] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0673] Step 1:

[0674] The user records audio data using their device. The audio recorded by the user includes elements that express specific emotions. This audio data is saved as a digital file on the device and stored in a temporary cache. The input data is raw audio data, and the result is an audio file ready to be sent to the server as output.

[0675] Step 2:

[0676] The user uploads audio data recorded via their device to the server. Simultaneously, the user selects a preferred song from the system's data collection. The selected song is also sent to the server. The input consists of the audio file and the selected song information, while the output is the status of the audio data's reception on the server.

[0677] Step 3:

[0678] The server receives the uploaded audio data and begins processing it with an analysis tool that identifies emotions. The analysis tool uses an audio machine learning algorithm to extract features from the audio data (such as tone, pitch, and tempo) and identify the user's emotions. The input is the audio data, and the output is the identified emotion information.

[0679] Step 4:

[0680] The server uses speech synthesis to integrate the identified emotion information with the selected song. This generates new voice data that corresponds to the emotion. A generative AI model is used in this process to create voice output that reflects the emotion. The input is emotion information and song data, and the output is the integrated voice data.

[0681] Step 5:

[0682] The server uses a generation mechanism to adjust the music and visual characteristics based on the audio data created in the previous step, generating the final media content. The tempo of the music and the color tones of the visuals are adjusted to match the identified emotion. The input is integrated audio data, and the output is the completed media content.

[0683] Step 6:

[0684] The server encodes the generated media content and delivers it to the user's terminal. During encoding, the optimal format and compression method are selected to ensure efficient transfer. The input is media content, and the output is a media file viewable on the user's terminal.

[0685] Step 7:

[0686] Users view media content received on their devices. After viewing, if they like the content, they can share it via social media, etc. The input is the media file received by the user, and the output is the experience of playing the content.

[0687] (Application Example 2)

[0688] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0689] The challenge is to create a system that generates content reflecting individual emotions based on the user's voice data, allowing them to enjoy a more personalized music experience.

[0690] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0691] In this invention, the server includes an emotion engine means that analyzes emotions from a user's voice data and generates personalized existing music data and video data selected based on that emotion data; a content generation means that generates integrated music and visual content using the voice data and video data that reflect the emotion information generated by the emotion engine means; and a communication means for distributing the integrated content to a communication terminal. This enables users to view and share personalized music videos that are tailored to their emotions.

[0692] "Audio data" is a collection of acoustic signals generated by a user's speech or voice.

[0693] An "emotion engine means" is a system or device for analyzing voice data to identify the user's emotions and generating data based on the identification results.

[0694] A "content generation method" is a system or device that generates new media by integrating music and visual elements based on emotional information.

[0695] "Communication means" refers to a system or device for transmitting generated digital content to another device via a network.

[0696] A "communication terminal" is a device used by users to receive and display digital content, and includes smartphones and tablets.

[0697] To realize this invention, the system first involves the user performing voice input using the terminal's microphone. The terminal uploads the recorded voice data to a server. The server analyzes the emotions from the voice data using an emotion engine and digitizes the results. This analysis uses speech recognition software (e.g., IBM Watson Tone Analyzer). Based on the analyzed emotion information, a content generation means generates personalized content incorporating music and visual elements. This generation process utilizes video editing software APIs (e.g., Adobe Premiere Pro API). Finally, the generated content is sent from the server to the communication terminal, making it available for the user to view. Internet connectivity is used for this communication.

[0698] For example, if a user says "I'm feeling great today," the server's emotion engine identifies this as "joy" and generates a music video combining upbeat music and cheerful visuals.

[0699] Examples of prompts for a generative AI model include the following:

[0700] "When a user is experiencing feelings of joy, generate music and visuals that match those feelings. The music should be upbeat, and the visuals should use bright colors."

[0701] In this way, users can enjoy personalized content that matches their own emotions.

[0702] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0703] Step 1:

[0704] The user inputs voice using the device. The device records the user's voice using its built-in microphone. This recorded data is saved as a digital audio file. As a result, the audio data becomes the input.

[0705] Step 2:

[0706] The terminal uploads the recorded audio data to the server. Here, the audio data is transferred to the server via a communication protocol between devices. The audio data is stored on the server and becomes the input for the next calculation process.

[0707] Step 3:

[0708] The server uses an emotion engine to analyze voice data and identify the user's emotions. A speech recognition API (e.g., IBM Watson Tone Analyzer) is used to identify emotions by analyzing the pitch and tone of the voice from the input voice data. Emotion labels (e.g., joy, sadness) are generated as output.

[0709] Step 4:

[0710] The server utilizes the acquired emotion data to provide emotional information to the content generation engine. The engine references video data and music libraries to select music and visual effects that match the emotion. Digital content is created using a content generation API (e.g., Adobe Premiere Pro API). As output, a personalized music video based on the specific emotion is generated.

[0711] Step 5:

[0712] The server encodes the generated content and streams it to the user's communication device. The encoded data enables efficient data transfer and supports smooth playback on the device. The user can complete the experience by viewing this content. Once the digital content is sent to the device, its output is provided visually.

[0713] This process allows users to receive and enjoy personalized content that reflects their own emotions.

[0714] 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.

[0715] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0716] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0717] 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.

[0718] Figure 9 shows an 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.

[0719] 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.

[0720] 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.

[0721] 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, motorcycles, etc., 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, for example, based 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.

[0722] 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."

[0723] 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.

[0724] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0725] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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 the like 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.

[0734] 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 as being incorporated by reference.

[0735] The following is further disclosed regarding the embodiments described above.

[0736] (Claim 1)

[0737] A speech synthesis means that analyzes the speech features input by the user and generates speech data by combining them with existing music data selected based on those features,

[0738] A video generation means generates a music video that integrates background music and visual content using the audio data generated by the aforementioned speech synthesis means,

[0739] Distribution means for delivering the aforementioned music video to a user terminal,

[0740] A system that includes this.

[0741] (Claim 2)

[0742] The system according to claim 1, further comprising means for providing a library containing multiple existing songs that can be selected by the user.

[0743] (Claim 3)

[0744] The system according to claim 1, further comprising a voice adjustment means for automatically adjusting the pitch and timing of the user's voice data.

[0745] "Example 1"

[0746] (Claim 1)

[0747] A generation means that analyzes voice information input by the user and generates voice information by combining it with existing music data selected based on that analysis,

[0748] A synthesis means that uses the audio information generated by the aforementioned generation means to generate music content that integrates background sounds and visual information,

[0749] A supply means for supplying the aforementioned music content to a user device,

[0750] A system that includes this.

[0751] (Claim 2)

[0752] The system according to claim 1, further comprising means for providing a collection of multiple existing music data that can be selected by the user.

[0753] (Claim 3)

[0754] The system according to claim 1, further comprising an adjustment means for automatically adjusting the pitch and temporal arrangement of the user's voice information.

[0755] "Application Example 1"

[0756] (Claim 1)

[0757] A speech synthesis means that analyzes the speech features input by the user and generates speech information by combining them with selected song information,

[0758] A video generation means that generates video information by integrating supplementary information and visual information using the audio information generated by the aforementioned speech synthesis means,

[0759] Distribution means for distributing the aforementioned video information to an end-user device,

[0760] A communication means for sharing video information generated via end-user devices,

[0761] A system that includes this.

[0762] (Claim 2)

[0763] The system according to claim 1, further comprising an information storage means that includes multiple song information selectable by the user.

[0764] (Claim 3)

[0765] The system according to claim 1, further comprising a voice adjustment means for automatically adjusting the pitch and time sequence of the user's voice information.

[0766] "Example 2 of combining an emotion engine"

[0767] (Claim 1)

[0768] An analytical method for identifying emotions from a user's speech,

[0769] A speech synthesis means that generates speech data by combining it with existing music data selected based on emotional information identified by the analysis means,

[0770] A generation means that uses the speech synthesis means to generate speech data, adjusts the characteristics of the music and visual characteristics according to emotion, and generates integrated media content.

[0771] Distribution means for distributing media content generated by the generation means to communication devices,

[0772] A system that includes this.

[0773] (Claim 2)

[0774] The system according to claim 1, further comprising means for providing a data set containing multiple existing music tracks that can be selected by the user.

[0775] (Claim 3)

[0776] The system according to claim 1, further comprising a voice adjustment means for automatically adjusting the pitch and timing of voice data based on emotional information.

[0777] "Application example 2 when combining with an emotional engine"

[0778] (Claim 1)

[0779] An emotion engine means that analyzes emotions from a user's voice data and generates personalized versions of existing music and video data selected based on that emotion data,

[0780] A content generation means that generates integrated music and visual content using audio and video data that reflect emotional information generated by the aforementioned emotion engine means,

[0781] A communication means for distributing the aforementioned integrated content to a communication terminal,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, further comprising means for providing a library from which the user can select from multiple music data and video data.

[0785] (Claim 3)

[0786] The system according to claim 1, further comprising an emotion analysis means for extracting emotional features from an audio signal. [Explanation of symbols]

[0787] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A speech synthesis means that analyzes the speech features input by the user and generates speech data by combining them with existing music data selected based on those features, A video generation means generates a music video that integrates background music and visual content using the audio data generated by the aforementioned speech synthesis means, Distribution means for delivering the aforementioned music video to a user terminal, A system that includes this.

2. The system according to claim 1, further comprising means for providing a library containing multiple existing songs that can be selected by the user.

3. The system according to claim 1, further comprising a voice adjustment means for automatically adjusting the pitch and timing of the user's voice data.

Images