system

Abstract

We provide the system. [Solution] A receiving means for acquiring sound data, An analysis means for converting the aforementioned sound data into text data, A translation means for converting the aforementioned text data into sign language action data, A generation means for generating sign language video based on the aforementioned sign language motion data, A display means for displaying the aforementioned sign language video, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, it is an important issue for hearing-impaired people to access information and communicate smoothly. Conventional sign language interpretation services require arrangements and schedule adjustments for sign language interpreters, making it difficult to provide quickly and on a wide scale. Also, there is a current situation where the demand for sign language interpretation that can be immediately used in various scenes such as multi-person events and daily life has not been fully met. To solve this, there is a need to develop a system that can convert voice into sign language in real time without the need for sign language interpreters and quickly transmit information to hearing-impaired people.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides the following means: A receiving means for acquiring sound data is used to collect audio from lectures and conversations. This sound data is converted into text data by an analysis means, and further converted into sign language motion data by a translation means. Subsequently, a generation means creates sign language video based on this sign language motion data. Finally, this sign language video is visually output by a display means. This constructs a system that converts audio into sign language in real time without the need for a sign language interpreter, enabling effective information transmission to the hearing impaired.

[0006] "Audio data" refers to data that represents sound as a digital or analog signal.

[0007] "Receiving means" refers to a device or function for acquiring sound data and incorporating it into the system.

[0008] "Analysis means" refers to the processing or technology used to analyze sound data and convert it into text data.

[0009] "Text data" refers to digital data that is stored or displayed as character information.

[0010] "Translation method" refers to an algorithm or process for converting text data into sign language action data.

[0011] "Sign language movement data" refers to data that contains instructions and coordinate information corresponding to sign language movements.

[0012] "Generation means" refers to a function or device for generating sign language video based on sign language motion data.

[0013] "Sign language video" refers to a video or animation created to visually represent sign language.

[0014] "Display means" refers to devices or technologies for visually presenting generated sign language videos.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a 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.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a 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.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The sign language interpretation system of the present invention provides information to the hearing impaired by displaying audio as sign language images in real time in situations such as lectures and meetings. This system includes receiving means, analysis means, translation means, generation means, and display means.

[0037] The user inputs sound data into the microphone device of the sign language interpretation system by making a sound. This sound data is converted into digital data by the terminal and sent to the server.

[0038] When the server receives this audio data, it analyzes it into text data using speech recognition technology. The speech recognition utilizes a highly accurate natural language processing model to precisely convert spoken content into text.

[0039] Next, the text data is converted into sign language movement data by a translation tool. The translation tool maintains information consistency by converting the text into appropriate sign language movements while considering the grammatical structure of sign language.

[0040] The generation method generates 3D model sign language videos based on sign language motion data. This generation method has the capability to create visually recognizable sign language animations in real time using computer graphics technology.

[0041] Ultimately, the device receives the generated sign language video and displays it on a monitor or hologram display. This allows the user to visually receive sign language in real time, improving the efficiency of communication.

[0042] This system eliminates the problem of sign language interpreter shortages and scheduling issues, enabling rapid sign language interpretation services in a variety of situations. For example, when experts present at academic conferences, hearing-impaired attendees can understand the presentation in real time. These advantages contribute to improving information access for the hearing impaired.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] When a user speaks, their voice is input through the system's microphone. The microphone receives the voice as an analog signal.

[0046] Step 2:

[0047] The terminal converts the analog audio signal from the microphone into digital data. After conversion, it compresses the digital audio data and prepares it for efficient transmission to the server.

[0048] Step 3:

[0049] The server receives the audio data transmitted from the terminal. The server analyzes the digital audio data using a speech recognition engine and converts it from audio to text data. This engine uses a language model to recognize even the finer details of pronunciation.

[0050] Step 4:

[0051] The server passes the obtained text data to a translation tool, which converts it into sign language action data. Translation is performed using sign language grammar rules and a dictionary database, aiming to preserve the meaning precisely.

[0052] Step 5:

[0053] The server generates 3D sign language videos based on translated sign language motion data. The generation method utilizes 3D animation technology to achieve dynamic expression of sign language movements.

[0054] Step 6:

[0055] The generated sign language video is sent from the server to the terminal. The compression technology used here minimizes streaming latency while maintaining high-quality video.

[0056] Step 7:

[0057] The terminal decodes the received sign language video and displays it on a monitor or hologram device. This allows users to visually receive sign language interpretation in real time and understand information efficiently.

[0058] (Example 1)

[0059] 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."

[0060] Conventional sign language interpretation systems sometimes lack sufficient accuracy and speed when converting audio to sign language video, resulting in inadequate information provision for the hearing impaired, particularly in lectures and conferences where real-time information is required. Furthermore, given the shortage of sign language interpreters and the difficulty in scheduling, there is a need for a system that can respond quickly.

[0061] 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.

[0062] In this invention, the server includes a conversion device that converts speech information into coded data, an analysis device that analyzes the coded data into character information, and a conversion device that converts the character information into visual language action data. This enables the generation of sign language videos in real time through high-precision speech analysis and rapid visual language conversion, making it possible to efficiently provide information to people with hearing impairments.

[0063] An "input device" is a device used to acquire voice information into a system.

[0064] A "conversion device" is a device used to convert acquired audio information into coded data or visual language action data.

[0065] An "analysis device" is a device that analyzes coded data and converts it into character information.

[0066] A "generation device" is a device that generates three-dimensional images based on visual language action data.

[0067] An "output device" is a device used to display the generated three-dimensional image to the user.

[0068] A "transmission device" is a device used to compress audio information and transmit it to other devices or systems.

[0069] A "three-dimensional model" is a data structure that represents digitally structured information in three dimensions and is used for visual representation.

[0070] This sign language interpretation system is designed to allow hearing-impaired individuals to receive audio information as sign language video in situations such as lectures and conferences. The specific implementation details are described below.

[0071] The user emits voice in a lecture hall or conference room. The voice information is acquired by an input device (e.g., a microphone) that the user possesses or that is placed in the venue. The acquired voice information is converted from an analog signal to digital data by a conversion device installed in the terminal for digital signal processing, and then transmitted to a server using a transmission device.

[0072] The server receives the transmitted digital audio data. The received data is converted into text information via an analysis device. This analysis utilizes highly accurate speech recognition technology and leverages a generative AI model to achieve high-precision text conversion. One example of a model that could be used is an open-source speech recognition API.

[0073] The converted text information is then converted into visual language action data by another conversion device on the server. This step takes into account the grammatical structure of sign language and processes the text data to accurately translate it into sign language action data. The conversion process implements a sign language-specific action dictionary database to ensure information consistency between languages.

[0074] Subsequently, the visual language action data is converted into a three-dimensional image on the server using a generation device that utilizes a three-dimensional model. The generated sign language image is rendered in real time and provided in a visually recognizable format. Advanced computer graphics software (e.g., Unity) can be used for this visualization.

[0075] The generated three-dimensional sign language video data is then transmitted to the terminal's output device. The terminal displays the video on a monitor or hologram display, allowing the user to visually receive the sign language information. As a result, hearing-impaired individuals can receive information in real time through sign language video, even in situations where audio information is being transmitted.

[0076] As a concrete example, let's consider real-time sign language interpretation at an academic conference. By inputting audio data from presentations at the conference into the system, people with hearing impairments can understand the content in real time. As an example of a prompt to the generative AI model, we can consider something like, "Please translate the content of the next presentation into sign language in real time."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The user inputs voice information into the system via an input device. Specifically, the user speaks into the microphone device. This operation acquires voice data in analog format.

[0080] Step 2:

[0081] The terminal converts analog audio data obtained from the input device into digital data. The conversion uses an AD converter in the conversion device. The input is analog audio, and the output is coded data in a digital format. This coded data is transmitted to the server in an optimized format for efficient processing.

[0082] Step 3:

[0083] The server receives coded data and converts it into character information using an analysis device. Specifically, it applies a speech recognition algorithm and utilizes a generative AI model to extract text. The input is coded data, and the output is analyzed character information. High-precision text conversion is achieved by utilizing natural language processing.

[0084] Step 4:

[0085] The server uses the analyzed textual information to convert it into visual language action data. A translation device is used to perform data conversion based on sign language grammar. The input is textual information, and the output is visual language action data corresponding to sign language. This process is carried out while maintaining the consistency of sign language expression.

[0086] Step 5:

[0087] The server generates three-dimensional images based on visual language action data. Using a generation device and advanced computer graphics technology, it renders sign language animations in real time. The input is action data, and the output is three-dimensional sign language video. This video is designed to be intuitively understandable to the user.

[0088] Step 6:

[0089] The terminal receives three-dimensional sign language video transmitted from the server and displays it using an output device. The video is displayed in real time on a monitor or hologram display. The input is three-dimensional video data, and the output is presented to the user as visual information. This allows people with hearing impairments to visually absorb information in lectures and meetings.

[0090] (Application Example 1)

[0091] 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."

[0092] Traditionally, hearing-impaired individuals have had to rely on sign language interpreters to obtain information, leading to problems with interpreter shortages and scheduling. Furthermore, the infrastructure for hearing-impaired individuals to smoothly access services in their living environments, such as physical stores, is not adequately developed. As a result, hearing-impaired individuals face limitations in accessing information and struggle to participate in society.

[0093] 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.

[0094] In this invention, the server includes a receiving means for acquiring audio information, an analysis means for converting the audio information into text information, and a translation means for converting the text information into sign language gesture information. This makes it possible for hearing-impaired individuals to receive explanations from store staff in real time as visual information.

[0095] "Auditory information" refers to data obtained from the generation of sound, and includes acoustic signals, including human voices.

[0096] "Receiving means" refers to devices or technical means for receiving audio information from an external source.

[0097] "Textual information" refers to data in string format that is obtained by converting audio information.

[0098] "Analysis means" refers to devices or technical means for converting audio information into text information.

[0099] "Sign language action information" refers to action data in the form of sign language, which is derived from textual information.

[0100] "Translation means" refers to devices or technical means for converting textual information into sign language gesture information.

[0101] "Visual information" refers to data in which sign language gestures are visually represented, and is usually presented as video.

[0102] "Generation means" refers to devices or technical means for generating visual information from sign language movement information.

[0103] "Display means" refers to devices or technical means for displaying generated visual information.

[0104] A "communication device" is a device or technical means for sending generated visual information to an external device or system for display.

[0105] "Application devices" refer to the devices and applications used to operate a system in an actual usage environment.

[0106] To implement this invention, the system has three main components: a server, a terminal, and a user. The server performs core processing that analyzes voice information and generates sign language action information. Specifically, the server uses a microphone device to receive voice information and converts it into text information using speech recognition software. By using a generative AI model, which is a highly accurate natural language processing model, for speech recognition, the system converts speech into text in a natural way.

[0107] Next, the server converts the textual information into sign language gesture information. This uses a translation algorithm that takes into account the grammatical structure of sign language to generate consistent sign language gesture information. Based on this sign language gesture information, computer graphics software, acting as a generation method, generates visual information using a 3D model. This allows the user to understand sign language as visual information.

[0108] The terminal's role is to display visual information transmitted from the server on the user's device. Monitors or smart glasses are used as display means, presenting visual information in real time. The application device dynamically transmits the generated visual information to the user's device via a communication device.

[0109] For example, if a hearing-impaired person wants to learn more about a product in a physical store, the explanation from the store clerk is received as audio information via a microphone. The server converts the audio into text information, and then translates it into sign language gestures. Based on the accurate gesture information generated by the AI ​​model, a 3D animation is created and displayed in real time on smart glasses or similar devices.

[0110] As an example of a prompt, when the voice prompt "Where is this product manufactured?" is converted into sign language, a message such as "Please display a sign language description of the teacup's manufacturer" might be generated. This allows the user to obtain information in real time.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The system acquires voice information emitted by the user using the device's microphone. The input is an audio signal, which is encoded as a digital signal for transmission to the server. The output is the digitized audio information.

[0114] Step 2:

[0115] The server analyzes the digital audio information received from the terminal using a speech recognition module. The input is digital audio information, which is then converted into text information with high accuracy using a generative AI model. The output is natural language text information.

[0116] Step 3:

[0117] The server translates the generated text information into sign language action information. The input is text information, and a translation algorithm that considers the grammatical structure of sign language is applied. The output is sign language action information. During this process, prompts are used to instruct the server on how to generate the sign language.

[0118] Step 4:

[0119] The server generates 3D animations using a visual information generation module based on sign language motion information. The input is sign language motion information, and computer graphics technology is used to create visual animations. The output is visual information of a 3D model.

[0120] Step 5:

[0121] The terminal receives visual information transmitted from the server and displays it on a monitor or smart glasses. The input is visual information of a 3D model, which is presented on the display so that the user can visually receive sign language in real time. The output is sign language video that reaches the user's eyes.

[0122] 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.

[0123] The sign language interpretation system of the present invention not only converts speech into sign language images, but also incorporates a function to recognize the user's emotions and adjust the sign language expression accordingly. This provides more natural and emotionally rich sign language interpretation.

[0124] The voices that users produce during lectures or conversations are input into the system's microphone device. This audio data is digitized by the terminal, compressed, and then sent to the server.

[0125] The server uses speech recognition technology to analyze the audio data into text data. This process also includes an emotion engine that analyzes the tone and tempo of the speech to determine the user's emotional state (e.g., joy, sadness, anger).

[0126] The obtained text data is converted into sign language motion data by a translation tool, but the sign language motion data is also adjusted based on the emotional information recognized by the emotion engine. For example, if the user is expressing anger, the sign language motions will be expressed in a more exaggerated way.

[0127] The generation method generates 3D sign language images in real time based on adjusted sign language motion data. During this process, emotional expressions are also visually emphasized, enabling more natural and richer sign language interpretation.

[0128] Finally, the terminal receives the generated sign language video and displays it on a monitor or hologram device. In this way, the user can visually understand the audio information and the emotions it conveys with high accuracy. This system provides effective communication support for the hearing impaired in a variety of situations, for example, by conveying the emotions of a politician giving a speech in real time.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user speaks during a lecture or conversation, and the audio is input to the system via a microphone. The microphone collects the input audio as an analog signal.

[0132] Step 2:

[0133] The terminal converts the received analog audio signal into digital data. This digital data is compressed while maintaining sound quality and prepared for transmission to the server.

[0134] Step 3:

[0135] The terminal transmits compressed digital audio data to the server over the network. This process is performed quickly to enable real-time processing.

[0136] Step 4:

[0137] The server inputs the received audio data into the speech recognition engine and converts it into text data. In parallel, the emotion engine analyzes the pitch and intensity of the speech to determine the user's emotions.

[0138] Step 5:

[0139] The server uses the analyzed text data and emotional information to convert the text into sign language motion data using a translation mechanism. The emotional information influences the intensity and speed of the sign language movements, resulting in a more natural expression.

[0140] Step 6:

[0141] The server generates sign language videos using 3D animation technology based on sign language motion data. The generated videos have rich expressions that reflect emotions.

[0142] Step 7:

[0143] The server sends the generated sign language video to the terminal. The terminal decodes this data and prepares it for display in the optimal format.

[0144] Step 8:

[0145] The terminal displays sign language images in real time on a monitor or hologram device. This allows users to visually and accurately understand the content and emotions of lectures and conversations.

[0146] (Example 2)

[0147] 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".

[0148] Conventional sign language interpretation systems simply convert audio data into sign language, which has the problem of not being able to adequately express the speaker's emotions and other auditory information. Furthermore, the lack of real-time capabilities in generating sign language video can hinder sophisticated communication. This invention aims to solve these problems and provide natural and dynamic sign language interpretation that takes emotions into account.

[0149] 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.

[0150] In this invention, the server includes an analysis means for analyzing audio data into text data, an emotion analysis means for analyzing the tone and tempo of the audio to determine emotion, and an adjustment means for translating the text data into sign language motion data and adjusting the sign language motion data based on the emotion information. This makes it possible to generate natural sign language video in real time, taking into account the speaker's emotions.

[0151] "Audio data" refers to data that represents the voice information spoken by a user in digital format.

[0152] "Receiving means" refers to a device or function for acquiring audio data.

[0153] "Conversion means" refers to a process or device for converting an analog audio signal into a digital signal.

[0154] "Compression methods" refer to technologies used to compress audio data to reduce the amount of data and enable more efficient transmission.

[0155] "Analysis means" refers to the process or technology of analyzing audio data and converting it into text data.

[0156] "Emotion analysis methods" are technologies that analyze the tone and tempo of voice data to determine the user's emotions.

[0157] "Translation means" refers to the technology or process for converting text data into sign language action data.

[0158] "Adjustment means" refers to a technique or process for modifying sign language action data based on emotional information.

[0159] "Generation means" refers to technology or equipment for generating 3D sign language images in real time based on sign language motion data.

[0160] "Display means" refers to a device or function for visually displaying the generated sign language video.

[0161] The sign language interpretation system of the present invention is designed to convert user-generated speech into sign language video while simultaneously providing natural sign language expressions that take emotions into consideration.

[0162] The system's implementation primarily involves three elements: terminals, servers, and users. Audio information emitted by users during lectures or conversations is captured by a microphone device connected to the terminal. The terminal uses an A / D conversion chip to convert this audio data into a digital signal, and then improves the audio quality through a noise reduction filter.

[0163] The acquired digital audio data is compressed on the terminal, and compression algorithms such as MP3 or AAC are used to efficiently transmit it to the server. This compressed data is sent to the server via the internet or the corporate network.

[0164] On the server, a speech recognition engine converts speech data into text data. During this process, an emotion analysis engine operates, evaluating the speaker's tone and tempo to determine the user's emotional state. These analysis results are integrated into the process of translating the text data into sign language motion data using machine translation technology.

[0165] Sign language motion data is further refined based on emotional information, and a generative AI model is used to generate 3D sign language video in real time. This makes it possible to express sign language dynamically by emphasizing visual effects.

[0166] The terminal ultimately displays 3D sign language images received from the server via a display or hologram device. This system structure allows hearing-impaired individuals to visually understand information, including the emotions of speakers during lectures and conversations.

[0167] For example, when a user asks questions during a school lesson, it is possible to accurately visualize the excitement and anticipation conveyed in the student's question using sign language and communicate it to other participants.

[0168] An example of a prompt is, "Generate a sign language interpretation that takes into account the emotions of this speech." This prompt prompts the system to generate and display a sign language video that includes emotions based on the audio information.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The user emits sound during a lecture or conversation. This sound is captured as an analog signal through a microphone device connected to the terminal. The terminal converts the analog audio signal into digital data using an A / D conversion chip. The input is an analog audio signal, and the output is digitized audio data.

[0172] Step 2:

[0173] The device processes digitized audio data using a compression algorithm to reduce its size. Specifically, it uses compression technologies such as MP3 and AAC. The input is digital audio data, and the output is compressed audio data.

[0174] Step 3:

[0175] Compressed audio data is sent from the terminal to the server. A communication line such as the internet or a LAN is used for data transfer. The input is compressed audio data, and the output is the server's reception status.

[0176] Step 4:

[0177] The server analyzes the received audio data using a speech recognition engine and converts it into text data. During this process, the content of the audio data is extracted as text information. The input is compressed audio data, and the output is text data.

[0178] Step 5:

[0179] The server uses an emotion analysis engine to analyze voice tone and tempo to estimate the user's emotions. Specific algorithms include phoneme analysis and intonation evaluation. The input is voice data, and the output is emotional information.

[0180] Step 6:

[0181] The server uses machine translation technology to convert text data into sign language motion data. During this process, emotional information is also integrated, and the sign language movements are adjusted to be more natural. The input is text data and emotional information, and the output is the adjusted sign language motion data.

[0182] Step 7:

[0183] The adjusted sign language motion data is converted into 3D sign language video in real time by the server's generated AI model. This enhances visual expression and enables richer sign language interpretation. The input is sign language motion data, and the output is 3D sign language video.

[0184] Step 8:

[0185] The terminal displays 3D sign language video received from the server on a hologram device or monitor. The user understands the audio content and emotions by visually receiving this video. The input is 3D sign language video, and the output is a visual display of the video.

[0186] (Application Example 2)

[0187] 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".

[0188] In providing communication support to users with hearing impairments, it is crucial to accurately convey not only the content of the spoken words but also the speaker's emotions and intentions. However, conventional sign language interpretation systems often fail to adequately reflect emotional expression, making natural and rich communication difficult.

[0189] 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.

[0190] In this invention, the server includes an acquisition means for acquiring acoustic data, an analysis means for converting the acoustic data into text data, and a translation means for converting the text data into sign language motion data and adjusting the sign language motion data based on the emotion analysis results. This makes it possible to reflect the user's emotions in sign language and enable natural and emotionally rich communication.

[0191] "Audio data" refers to information that represents speech or sound in digital format.

[0192] "Acquisition means" refers to a configuration that has the function of collecting acoustic data and inputting it into a digital device.

[0193] "Analysis means" refers to a device or function that performs the process of converting acquired acoustic data into text data.

[0194] "Text data" refers to information represented in text format, which is a conversion of speech into linguistic expression.

[0195] A "translation method" is a configuration that converts text data into sign language motion data and also has the function of adjusting the sign language motion data based on the results of emotion analysis.

[0196] "Sign language action data" refers to a series of data representing actions that indicate sign language expressions.

[0197] "Generation means" refers to a device or function that creates three-dimensional sign language video based on adjusted sign language motion data.

[0198] "Display means" refers to a device or apparatus that visually outputs the generated three-dimensional sign language video.

[0199] "Emotional analysis results" refer to information indicating the emotional state analyzed from acoustic data.

[0200] The system for realizing this application consists of a process that acquires acoustic data, analyzes emotions from the speech, and generates and displays three-dimensional sign language video. The details are shown below.

[0201] The server receives audio data acquired through smartphones or dedicated audio input devices. This audio data is converted into text data using a speech recognition engine (e.g., Google® Cloud Speech-to-Text). At the same time, an emotion analysis engine (e.g., IBM Watson® Tone Analyzer) is used to generate emotion analysis results from the audio. Based on this emotion analysis, the translation system converts the text data into sign language gesture data and further adjusts it to reflect emotions.

[0202] Next, the generation means generates a three-dimensional sign language video in real time using the adjusted sign language motion data, and outputs it to the display means, i.e., the user's smartphone or a connected display.

[0203] For example, in a scene where a staff member at a nursing home cheerfully asks an elderly resident, "It's a nice day today, shall we go for a walk?", the server can interpret that emotion and add cheerful expressions to the sign language video. In this way, the elderly can gain a deeper understanding of the intentions and emotions behind the care staff's suggestion.

[0204] An example of a prompt for the generation AI model is, "Please reflect positive emotions from the audio data into the sign language video so that elderly people can understand it."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The user acquires audio data (sound) using a smartphone or a dedicated audio input device. The input is real-time audio data, and the output is digital audio data.

[0208] Step 2:

[0209] The terminal sends the acquired audio data to the server. The server inputs the received audio data into a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts it into text data. The input is audio data, and the output is text data. In this process, speech extraction and text conversion are performed using audio signal processing.

[0210] Step 3:

[0211] The server simultaneously uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the audio data. The input for this step is the audio data, and the output is the emotion analysis result. Elements such as tone, tempo, and emphasis are analyzed.

[0212] Step 4:

[0213] The server uses translation tools to convert text data and sentiment analysis results into sign language action data. Furthermore, it adjusts the sign language action data based on the sentiment analysis results. The input is text data and sentiment analysis results, and the output is the adjusted sign language action data.

[0214] Step 5:

[0215] The server uses a generation mechanism to generate three-dimensional sign language video in real time based on adjusted sign language motion data. The input is adjusted sign language motion data, and the output is three-dimensional sign language video. 3D modeling and animation generation are performed here.

[0216] Step 6:

[0217] The device receives the generated three-dimensional sign language video and displays it on the user's smartphone or a connected display. The input is three-dimensional sign language video, and the output is a visually displayed image. In this way, the user can visually understand the audio information and its emotions.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] The sign language interpretation system of the present invention provides information to the hearing impaired by displaying audio as sign language images in real time at lectures, conferences, and other similar events. This system includes receiving means, analysis means, translation means, generation means, and display means.

[0235] The user inputs sound data into the microphone device of the sign language interpretation system by making a sound. This sound data is converted into digital data by the terminal and sent to the server.

[0236] When the server receives this audio data, it analyzes it into text data using speech recognition technology. The speech recognition utilizes a highly accurate natural language processing model to precisely convert spoken content into text.

[0237] Next, the text data is converted into sign language movement data by a translation tool. The translation tool maintains information consistency by converting the text into appropriate sign language movements while considering the grammatical structure of sign language.

[0238] The generation method generates 3D model sign language videos based on sign language motion data. This generation method has the capability to create visually recognizable sign language animations in real time using computer graphics technology.

[0239] Ultimately, the device receives the generated sign language video and displays it on a monitor or hologram display. This allows the user to visually receive sign language in real time, improving the efficiency of communication.

[0240] This system eliminates the problem of sign language interpreter shortages and scheduling issues, enabling rapid sign language interpretation services in a variety of situations. For example, when experts present at academic conferences, hearing-impaired attendees can understand the presentation in real time. These advantages contribute to improving information access for the hearing impaired.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] When a user speaks, their voice is input through the system's microphone. The microphone receives the voice as an analog signal.

[0244] Step 2:

[0245] The terminal converts the analog audio signal from the microphone into digital data. After conversion, it compresses the digital audio data and prepares it for efficient transmission to the server.

[0246] Step 3:

[0247] The server receives the audio data transmitted from the terminal. The server analyzes the digital audio data using a speech recognition engine and converts it from audio to text data. This engine uses a language model to recognize even the finer details of pronunciation.

[0248] Step 4:

[0249] The server passes the obtained text data to a translation tool, which converts it into sign language action data. Translation is performed using sign language grammar rules and a dictionary database, aiming to preserve the meaning precisely.

[0250] Step 5:

[0251] The server generates 3D sign language videos based on translated sign language motion data. The generation method utilizes 3D animation technology to achieve dynamic expression of sign language movements.

[0252] Step 6:

[0253] The generated sign language video is sent from the server to the terminal. The compression technology used here minimizes streaming latency while maintaining high-quality video.

[0254] Step 7:

[0255] The terminal decodes the received sign language video and displays it on a monitor or hologram device. This allows users to visually receive sign language interpretation in real time and understand information efficiently.

[0256] (Example 1)

[0257] 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."

[0258] Conventional sign language interpretation systems sometimes lack sufficient accuracy and speed when converting audio to sign language video, resulting in inadequate information provision for the hearing impaired, particularly in lectures and conferences where real-time information is required. Furthermore, given the shortage of sign language interpreters and the difficulty in scheduling, there is a need for a system that can respond quickly.

[0259] 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.

[0260] In this invention, the server includes a conversion device that converts speech information into coded data, an analysis device that analyzes the coded data into character information, and a conversion device that converts the character information into visual language action data. This enables the generation of sign language videos in real time through high-precision speech analysis and rapid visual language conversion, making it possible to efficiently provide information to people with hearing impairments.

[0261] An "input device" is a device used to acquire voice information into a system.

[0262] A "conversion device" is a device used to convert acquired audio information into coded data or visual language action data.

[0263] An "analysis device" is a device that analyzes coded data and converts it into character information.

[0264] A "generation device" is a device that generates three-dimensional images based on visual language action data.

[0265] An "output device" is a device used to display the generated three-dimensional image to the user.

[0266] A "transmission device" is a device used to compress audio information and transmit it to other devices or systems.

[0267] A "three-dimensional model" is a data structure that represents digitally structured information in three dimensions and is used for visual representation.

[0268] This sign language interpretation system is designed to allow hearing-impaired individuals to receive audio information as sign language video in situations such as lectures and conferences. The specific implementation details are described below.

[0269] The user emits voice in a lecture hall or conference room. The voice information is acquired by an input device (e.g., a microphone) that the user possesses or that is placed in the venue. The acquired voice information is converted from an analog signal to digital data by a conversion device installed in the terminal for digital signal processing, and then transmitted to a server using a transmission device.

[0270] The server receives the transmitted digital audio data. The received data is converted into text information via an analysis device. This analysis utilizes highly accurate speech recognition technology and leverages a generative AI model to achieve high-precision text conversion. One example of a model that could be used is an open-source speech recognition API.

[0271] The converted text information is then converted into visual language action data by another conversion device on the server. This step takes into account the grammatical structure of sign language and processes the text data to accurately translate it into sign language action data. The conversion process implements a sign language-specific action dictionary database to ensure information consistency between languages.

[0272] Subsequently, the visual language action data is converted into a three-dimensional image on the server using a generation device that utilizes a three-dimensional model. The generated sign language image is rendered in real time and provided in a visually recognizable format. Advanced computer graphics software (e.g., Unity) can be used for this visualization.

[0273] The generated three-dimensional sign language video data is then transmitted to the terminal's output device. The terminal displays the video on a monitor or hologram display, allowing the user to visually receive the sign language information. As a result, hearing-impaired individuals can receive information in real time through sign language video, even in situations where audio information is being transmitted.

[0274] As a concrete example, let's consider real-time sign language interpretation at an academic conference. By inputting audio data from presentations at the conference into the system, people with hearing impairments can understand the content in real time. As an example of a prompt to the generative AI model, we can consider something like, "Please translate the content of the next presentation into sign language in real time."

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The user inputs voice information into the system via an input device. Specifically, the user speaks into the microphone device. This operation acquires voice data in analog format.

[0278] Step 2:

[0279] The terminal converts analog audio data obtained from the input device into digital data. The conversion uses an AD converter in the conversion device. The input is analog audio, and the output is coded data in a digital format. This coded data is transmitted to the server in an optimized format for efficient processing.

[0280] Step 3:

[0281] The server receives the coded data and converts it into character information by an analysis device. Specifically, it applies a speech recognition algorithm and utilizes a generated AI model to extract text. The input is the coded data, and the output is the analyzed character information. High-precision text conversion is performed by leveraging natural language processing.

[0282] Step 4:

[0283] The server uses the analyzed character information to convert it into visual language action data. Using a translation device, data conversion based on sign language grammar is performed. The input is the character information, and the output is the visual language action data corresponding to sign language. This process is carried out while maintaining the consistency of sign language expressions.

[0284] Step 5:

[0285] The server generates a three-dimensional video based on the visual language action data. Using a generation device, it makes full use of computer graphics technology to draw sign language animations in real time. The input is the action data, and the output is a three-dimensional sign language video. This video is designed so that users can intuitively understand it.

[0286] Step 6:

[0287] The terminal receives the three-dimensional sign language video transmitted from the server and displays it on an output device. The video is projected in real time on a monitor or a holographic display. The input is the three-dimensional video data, and the output is presented to the user as visual information. As a result, the hearing-impaired can visually absorb information at lectures and meetings.

[0288] (Application Example 1)

[0289] Next, Application Example 1 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".

[0290] Traditionally, hearing-impaired individuals have had to rely on sign language interpreters to obtain information, leading to problems with interpreter shortages and scheduling. Furthermore, the infrastructure for hearing-impaired individuals to smoothly access services in their living environments, such as physical stores, is not adequately developed. As a result, hearing-impaired individuals face limitations in accessing information and struggle to participate in society.

[0291] 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.

[0292] In this invention, the server includes a receiving means for acquiring audio information, an analysis means for converting the audio information into text information, and a translation means for converting the text information into sign language gesture information. This makes it possible for hearing-impaired individuals to receive explanations from store staff in real time as visual information.

[0293] "Auditory information" refers to data obtained from the generation of sound, and includes acoustic signals, including human voices.

[0294] "Receiving means" refers to devices or technical means for receiving audio information from an external source.

[0295] "Textual information" refers to data in string format that is obtained by converting audio information.

[0296] "Analysis means" refers to devices or technical means for converting audio information into text information.

[0297] "Sign language action information" refers to action data in the form of sign language, which is derived from textual information.

[0298] "Translation means" refers to devices or technical means for converting textual information into sign language gesture information.

[0299] "Visual information" refers to data in which sign language gestures are visually represented, and is usually presented as video.

[0300] "Generation means" refers to devices or technical means for generating visual information from sign language movement information.

[0301] "Display means" refers to devices or technical means for displaying generated visual information.

[0302] A "communication device" is a device or technical means for sending generated visual information to an external device or system for display.

[0303] "Application devices" refer to the devices and applications used to operate a system in an actual usage environment.

[0304] To implement this invention, the system has three main components: a server, a terminal, and a user. The server performs core processing that analyzes voice information and generates sign language action information. Specifically, the server uses a microphone device to receive voice information and converts it into text information using speech recognition software. By using a generative AI model, which is a highly accurate natural language processing model, for speech recognition, the system converts speech into text in a natural way.

[0305] Next, the server converts the textual information into sign language gesture information. This uses a translation algorithm that takes into account the grammatical structure of sign language to generate consistent sign language gesture information. Based on this sign language gesture information, computer graphics software, acting as a generation method, generates visual information using a 3D model. This allows the user to understand sign language as visual information.

[0306] The terminal's role is to display visual information transmitted from the server on the user's device. Monitors or smart glasses are used as display means, presenting visual information in real time. The application device dynamically transmits the generated visual information to the user's device via a communication device.

[0307] For example, when a person with hearing impairment wants to know more about a product in a physical store, the explanation by the store clerk is received by a microphone as audio information. The server converts the audio into character information and further translates it into sign language motion information. Based on the accurate motion information from the generative AI model, a 3D animation is generated and displayed in real time on smart glasses or the like.

[0308] As an example of a prompt sentence, when a voice such as "Where is the manufacturer of this product?" is converted into sign language, content such as "Please display an explanation of the manufacturer of the teacup in sign language." is generated. This enables the user to obtain information in real time.

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The audio information uttered by the user is acquired by the microphone device of the terminal. The input is an audio signal, which is encoded as a digital signal for transmission to the server. The output is digitized audio information.

[0312] Step 2:

[0313] The server analyzes the digital audio information received from the terminal using an audio recognition module. The input is digital audio information, which is accurately converted into character information using a generative AI model. The output is character information in natural language.

[0314] Step 3:

[0315] The server translates the generated character information into sign language motion information. The input is character information, and a translation algorithm considering the grammar structure of sign language is applied. The output is sign language motion information. At this time, a prompt sentence is used to give instructions for sign language generation.

[0316] Step 4:

[0317] The server generates 3D animations using a visual information generation module based on sign language motion information. The input is sign language motion information, and computer graphics technology is used to create visual animations. The output is visual information of a 3D model.

[0318] Step 5:

[0319] The terminal receives visual information transmitted from the server and displays it on a monitor or smart glasses. The input is visual information of a 3D model, which is presented on the display so that the user can visually receive sign language in real time. The output is sign language video that reaches the user's eyes.

[0320] 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.

[0321] The sign language interpretation system of the present invention not only converts speech into sign language images, but also incorporates a function to recognize the user's emotions and adjust the sign language expression accordingly. This provides more natural and emotionally rich sign language interpretation.

[0322] The voices that users produce during lectures or conversations are input into the system's microphone device. This audio data is digitized by the terminal, compressed, and then sent to the server.

[0323] The server uses speech recognition technology to analyze the audio data into text data. This process also includes an emotion engine that analyzes the tone and tempo of the speech to determine the user's emotional state (e.g., joy, sadness, anger).

[0324] The obtained text data is converted into sign language motion data by a translation tool, but the sign language motion data is also adjusted based on the emotional information recognized by the emotion engine. For example, if the user is expressing anger, the sign language motions will be expressed in a more exaggerated way.

[0325] The generation method generates 3D sign language images in real time based on adjusted sign language motion data. During this process, emotional expressions are also visually emphasized, enabling more natural and richer sign language interpretation.

[0326] Finally, the terminal receives the generated sign language video and displays it on a monitor or hologram device. In this way, the user can visually understand the audio information and the emotions it conveys with high accuracy. This system provides effective communication support for the hearing impaired in a variety of situations, for example, by conveying the emotions of a politician giving a speech in real time.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The user speaks during a lecture or conversation, and the audio is input to the system via a microphone. The microphone collects the input audio as an analog signal.

[0330] Step 2:

[0331] The terminal converts the received analog audio signal into digital data. This digital data is compressed while maintaining sound quality and prepared for transmission to the server.

[0332] Step 3:

[0333] The terminal transmits compressed digital audio data to the server over the network. This process is performed quickly to enable real-time processing.

[0334] Step 4:

[0335] The server inputs the received audio data into the speech recognition engine and converts it into text data. In parallel, the emotion engine analyzes the pitch and intensity of the speech to determine the user's emotions.

[0336] Step 5:

[0337] The server uses the analyzed text data and emotional information to convert the text into sign language motion data using a translation mechanism. The emotional information influences the intensity and speed of the sign language movements, resulting in a more natural expression.

[0338] Step 6:

[0339] The server generates sign language videos using 3D animation technology based on sign language motion data. The generated videos have rich expressions that reflect emotions.

[0340] Step 7:

[0341] The server sends the generated sign language video to the terminal. The terminal decodes this data and prepares it for display in the optimal format.

[0342] Step 8:

[0343] The terminal displays sign language images in real time on a monitor or hologram device. This allows users to visually and accurately understand the content and emotions of lectures and conversations.

[0344] (Example 2)

[0345] 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 glasses 214 will be referred to as the "terminal".

[0346] Conventional sign language interpretation systems simply convert audio data into sign language, which has the problem of not being able to adequately express the speaker's emotions and other auditory information. Furthermore, the lack of real-time capabilities in generating sign language video can hinder sophisticated communication. This invention aims to solve these problems and provide natural and dynamic sign language interpretation that takes emotions into account.

[0347] 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.

[0348] In this invention, the server includes an analysis means for analyzing audio data into text data, an emotion analysis means for analyzing the tone and tempo of the audio to determine emotion, and an adjustment means for translating the text data into sign language motion data and adjusting the sign language motion data based on the emotion information. This makes it possible to generate natural sign language video in real time, taking into account the speaker's emotions.

[0349] "Audio data" refers to data that represents the voice information spoken by a user in digital format.

[0350] "Receiving means" refers to a device or function for acquiring audio data.

[0351] "Conversion means" refers to a process or device for converting analog audio signals into digital signals.

[0352] "Compression methods" refer to technologies used to compress audio data to reduce the amount of data and enable more efficient transmission.

[0353] "Analysis means" refers to the process or technology of analyzing audio data and converting it into text data.

[0354] "Emotion analysis methods" are technologies that analyze the tone and tempo of voice data to determine the user's emotions.

[0355] "Translation means" refers to the technology or process for converting text data into sign language action data.

[0356] "Adjustment means" refers to a technique or process for modifying sign language action data based on emotional information.

[0357] "Generation means" refers to technology or equipment for generating 3D sign language images in real time based on sign language motion data.

[0358] "Display means" refers to a device or function for visually displaying the generated sign language video.

[0359] The sign language interpretation system of the present invention is designed to convert user-generated speech into sign language video while simultaneously providing natural sign language expressions that take emotions into consideration.

[0360] The system's implementation primarily involves three elements: terminals, servers, and users. Audio information emitted by users during lectures or conversations is captured by a microphone device connected to the terminal. The terminal uses an A / D conversion chip to convert this audio data into a digital signal, and then improves the audio quality through a noise reduction filter.

[0361] The acquired digital audio data is compressed on the terminal, and compression algorithms such as MP3 or AAC are used to efficiently transmit it to the server. This compressed data is sent to the server via the internet or the corporate network.

[0362] On the server, a speech recognition engine converts speech data into text data. During this process, an emotion analysis engine operates, evaluating the speaker's tone and tempo to determine the user's emotional state. These analysis results are integrated into the process of translating the text data into sign language motion data using machine translation technology.

[0363] Sign language motion data is further refined based on emotional information, and a generative AI model is used to generate 3D sign language video in real time. This makes it possible to express sign language dynamically by emphasizing visual effects.

[0364] The terminal ultimately displays 3D sign language images received from the server via a display or hologram device. This system structure allows hearing-impaired individuals to visually understand information, including the emotions of speakers during lectures and conversations.

[0365] For example, when a user asks questions during a school lesson, it is possible to accurately visualize the excitement and anticipation conveyed in the student's question using sign language and communicate it to other participants.

[0366] An example of a prompt is, "Generate a sign language interpretation that takes into account the emotions of this speech." This prompt prompts the system to generate and display a sign language video that includes emotions based on the audio information.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The user emits sound during a lecture or conversation. This sound is captured as an analog signal through a microphone device connected to the terminal. The terminal converts the analog audio signal into digital data using an A / D conversion chip. The input is an analog audio signal, and the output is digitized audio data.

[0370] Step 2:

[0371] The device processes digitized audio data using a compression algorithm to reduce its size. Specifically, it uses compression technologies such as MP3 and AAC. The input is digital audio data, and the output is compressed audio data.

[0372] Step 3:

[0373] Compressed audio data is sent from the terminal to the server. A communication line such as the internet or a LAN is used for data transfer. The input is compressed audio data, and the output is the server's reception status.

[0374] Step 4:

[0375] The server analyzes the received audio data using a speech recognition engine and converts it into text data. During this process, the content of the audio data is extracted as text information. The input is compressed audio data, and the output is text data.

[0376] Step 5:

[0377] The server uses an emotion analysis engine to analyze voice tone and tempo to estimate the user's emotions. Specific algorithms include phoneme analysis and intonation evaluation. The input is voice data, and the output is emotional information.

[0378] Step 6:

[0379] The server uses machine translation technology to convert text data into sign language motion data. During this process, emotional information is also integrated, and the sign language movements are adjusted to be more natural. The input is text data and emotional information, and the output is the adjusted sign language motion data.

[0380] Step 7:

[0381] The adjusted sign language motion data is converted into 3D sign language video in real time by the server's generated AI model. This enhances visual expression and enables richer sign language interpretation. The input is sign language motion data, and the output is 3D sign language video.

[0382] Step 8:

[0383] The terminal displays 3D sign language video received from the server on a hologram device or monitor. The user understands the audio content and emotions by visually receiving this video. The input is 3D sign language video, and the output is a visual display of the video.

[0384] (Application Example 2)

[0385] 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 will be referred to as the "terminal."

[0386] In providing communication support to users with hearing impairments, it is crucial to accurately convey not only the content of the spoken words but also the speaker's emotions and intentions. However, conventional sign language interpretation systems often fail to adequately reflect emotional expression, making natural and rich communication difficult.

[0387] 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.

[0388] In this invention, the server includes an acquisition means for acquiring acoustic data, an analysis means for converting the acoustic data into text data, and a translation means for converting the text data into sign language motion data and adjusting the sign language motion data based on the emotion analysis results. This makes it possible to reflect the user's emotions in sign language and enable natural and emotionally rich communication.

[0389] "Audio data" refers to information that represents speech or sound in digital format.

[0390] "Acquisition means" refers to a configuration that has the function of collecting acoustic data and inputting it into a digital device.

[0391] "Analysis means" refers to a device or function that performs the process of converting acquired acoustic data into text data.

[0392] "Text data" refers to information represented in text format, which is a conversion of speech into linguistic expression.

[0393] A "translation method" is a configuration that converts text data into sign language motion data and also has the function of adjusting the sign language motion data based on the results of emotion analysis.

[0394] "Sign language action data" refers to a series of data representing actions that indicate sign language expressions.

[0395] "Generation means" refers to a device or function that creates three-dimensional sign language video based on adjusted sign language motion data.

[0396] "Display means" refers to a device or apparatus that visually outputs the generated three-dimensional sign language video.

[0397] "Emotional analysis results" refer to information indicating the emotional state analyzed from acoustic data.

[0398] The system for realizing this application consists of a process that acquires acoustic data, analyzes emotions from the speech, and generates and displays three-dimensional sign language video. The details are shown below.

[0399] The server receives audio data acquired through smartphones or dedicated audio input devices. This audio data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). At the same time, an emotion analysis engine (e.g., IBM Watson Tone Analyzer) is used to generate emotion analysis results from the audio. Based on this emotion analysis, the translation system converts the text data into sign language gesture data and further adjusts it to reflect emotions.

[0400] Next, the generation means generates a three-dimensional sign language video in real time using the adjusted sign language motion data, and outputs it to the display means, i.e., the user's smartphone or a connected display.

[0401] For example, in a scene where a staff member at a nursing home cheerfully asks an elderly resident, "It's a nice day today, shall we go for a walk?", the server can interpret that emotion and add cheerful expressions to the sign language video. In this way, the elderly can gain a deeper understanding of the intentions and emotions behind the care staff's suggestion.

[0402] An example of a prompt for the generation AI model is, "Please reflect positive emotions from the audio data into the sign language video so that elderly people can understand it."

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The user acquires audio data (sound) using a smartphone or a dedicated audio input device. The input is real-time audio data, and the output is digital audio data.

[0406] Step 2:

[0407] The terminal sends the acquired audio data to the server. The server inputs the received audio data into a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts it into text data. The input is audio data, and the output is text data. In this process, speech extraction and text conversion are performed using audio signal processing.

[0408] Step 3:

[0409] The server simultaneously uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the audio data. The input for this step is the audio data, and the output is the emotion analysis result. Elements such as tone, tempo, and emphasis are analyzed.

[0410] Step 4:

[0411] The server uses translation tools to convert text data and sentiment analysis results into sign language action data. Furthermore, it adjusts the sign language action data based on the sentiment analysis results. The input is text data and sentiment analysis results, and the output is the adjusted sign language action data.

[0412] Step 5:

[0413] The server uses a generation mechanism to generate three-dimensional sign language video in real time based on adjusted sign language motion data. The input is adjusted sign language motion data, and the output is three-dimensional sign language video. 3D modeling and animation generation are performed here.

[0414] Step 6:

[0415] The device receives the generated three-dimensional sign language video and displays it on the user's smartphone or a connected display. The input is three-dimensional sign language video, and the output is a visually displayed image. In this way, the user can visually understand the audio information and its emotions.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] The sign language interpretation system of the present invention provides information to the hearing impaired by displaying audio as sign language images in real time at lectures, conferences, and other similar events. This system includes receiving means, analysis means, translation means, generation means, and display means.

[0433] The user inputs sound data into the microphone device of the sign language interpretation system by making a sound. This sound data is converted into digital data by the terminal and sent to the server.

[0434] When the server receives this audio data, it analyzes it into text data using speech recognition technology. The speech recognition utilizes a highly accurate natural language processing model to precisely convert spoken content into text.

[0435] Next, the text data is converted into sign language movement data by a translation tool. The translation tool maintains information consistency by converting the text into appropriate sign language movements while considering the grammatical structure of sign language.

[0436] The generation method generates 3D model sign language videos based on sign language motion data. This generation method has the capability to create visually recognizable sign language animations in real time using computer graphics technology.

[0437] Ultimately, the device receives the generated sign language video and displays it on a monitor or hologram display. This allows the user to visually receive sign language in real time, improving the efficiency of communication.

[0438] This system eliminates the problem of sign language interpreter shortages and scheduling issues, enabling rapid sign language interpretation services in a variety of situations. For example, when experts present at academic conferences, hearing-impaired attendees can understand the presentation in real time. These advantages contribute to improving information access for the hearing impaired.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] When a user speaks, their voice is input through the system's microphone. The microphone receives the voice as an analog signal.

[0442] Step 2:

[0443] The terminal converts the analog audio signal from the microphone into digital data. After conversion, it compresses the digital audio data and prepares it for efficient transmission to the server.

[0444] Step 3:

[0445] The server receives the audio data transmitted from the terminal. The server analyzes the digital audio data using a speech recognition engine and converts it from audio to text data. This engine uses a language model to recognize even the finer details of pronunciation.

[0446] Step 4:

[0447] The server passes the obtained text data to a translation tool, which converts it into sign language action data. Translation is performed using sign language grammar rules and a dictionary database, aiming to preserve the meaning precisely.

[0448] Step 5:

[0449] The server generates 3D sign language videos based on translated sign language motion data. The generation method utilizes 3D animation technology to achieve dynamic expression of sign language movements.

[0450] Step 6:

[0451] The generated sign language video is sent from the server to the terminal. The compression technology used here minimizes streaming latency while maintaining high-quality video.

[0452] Step 7:

[0453] The terminal decodes the received sign language video and displays it on a monitor or hologram device. This allows users to visually receive sign language interpretation in real time and understand information efficiently.

[0454] (Example 1)

[0455] 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."

[0456] Conventional sign language interpretation systems sometimes lack sufficient accuracy and speed when converting audio to sign language video, resulting in inadequate information provision for the hearing impaired, particularly in lectures and conferences where real-time information is required. Furthermore, given the shortage of sign language interpreters and the difficulty in scheduling, there is a need for a system that can respond quickly.

[0457] 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.

[0458] In this invention, the server includes a conversion device that converts speech information into coded data, an analysis device that analyzes the coded data into character information, and a conversion device that converts the character information into visual language action data. This enables the generation of sign language videos in real time through high-precision speech analysis and rapid visual language conversion, making it possible to efficiently provide information to people with hearing impairments.

[0459] An "input device" is a device used to acquire voice information into a system.

[0460] A "conversion device" is a device used to convert acquired audio information into coded data or visual language action data.

[0461] An "analysis device" is a device that analyzes coded data and converts it into character information.

[0462] A "generation device" is a device that generates three-dimensional images based on visual language action data.

[0463] An "output device" is a device used to display the generated three-dimensional image to the user.

[0464] A "transmission device" is a device used to compress audio information and transmit it to other devices or systems.

[0465] A "three-dimensional model" is a data structure that represents digitally structured information in three dimensions and is used for visual representation.

[0466] This sign language interpretation system is designed to allow hearing-impaired individuals to receive audio information as sign language video in situations such as lectures and conferences. The specific implementation details are described below.

[0467] The user emits voice in a lecture hall or conference room. The voice information is acquired by an input device (e.g., a microphone) that the user possesses or that is placed in the venue. The acquired voice information is converted from an analog signal to digital data by a conversion device installed in the terminal for digital signal processing, and then transmitted to a server using a transmission device.

[0468] The server receives the transmitted digital audio data. The received data is converted into text information via an analysis device. This analysis utilizes highly accurate speech recognition technology and leverages a generative AI model to achieve high-precision text conversion. One example of a model that could be used is an open-source speech recognition API.

[0469] The converted text information is then converted into visual language action data by another conversion device on the server. This step takes into account the grammatical structure of sign language and processes the text data to accurately translate it into sign language action data. The conversion process implements a sign language-specific action dictionary database to ensure information consistency between languages.

[0470] Subsequently, the visual language action data is converted into a three-dimensional image on the server using a generation device that utilizes a three-dimensional model. The generated sign language image is rendered in real time and provided in a visually recognizable format. Advanced computer graphics software (e.g., Unity) can be used for this visualization.

[0471] The generated three-dimensional sign language video data is then transmitted to the terminal's output device. The terminal displays the video on a monitor or hologram display, allowing the user to visually receive the sign language information. As a result, hearing-impaired individuals can receive information in real time through sign language video, even in situations where audio information is being transmitted.

[0472] As a concrete example, let's consider real-time sign language interpretation at an academic conference. By inputting audio data from presentations at the conference into the system, people with hearing impairments can understand the content in real time. As an example of a prompt to the generative AI model, we can consider something like, "Please translate the content of the next presentation into sign language in real time."

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The user inputs voice information into the system via an input device. Specifically, the user speaks into the microphone device. This operation acquires voice data in analog format.

[0476] Step 2:

[0477] The terminal converts analog audio data obtained from the input device into digital data. The conversion uses an AD converter in the conversion device. The input is analog audio, and the output is coded data in a digital format. This coded data is transmitted to the server in an optimized format for efficient processing.

[0478] Step 3:

[0479] The server receives coded data and converts it into character information using an analysis device. Specifically, it applies a speech recognition algorithm and utilizes a generative AI model to extract text. The input is coded data, and the output is analyzed character information. High-precision text conversion is achieved by utilizing natural language processing.

[0480] Step 4:

[0481] The server uses the analyzed textual information to convert it into visual language action data. A translation device is used to perform data conversion based on sign language grammar. The input is textual information, and the output is visual language action data corresponding to sign language. This process is carried out while maintaining the consistency of sign language expression.

[0482] Step 5:

[0483] The server generates three-dimensional images based on visual language action data. Using a generation device and advanced computer graphics technology, it renders sign language animations in real time. The input is action data, and the output is three-dimensional sign language video. This video is designed to be intuitively understandable to the user.

[0484] Step 6:

[0485] The terminal receives three-dimensional sign language video transmitted from the server and displays it using an output device. The video is displayed in real time on a monitor or hologram display. The input is three-dimensional video data, and the output is presented to the user as visual information. This allows people with hearing impairments to visually absorb information in lectures and meetings.

[0486] (Application Example 1)

[0487] 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."

[0488] Traditionally, hearing-impaired individuals have had to rely on sign language interpreters to obtain information, leading to problems with interpreter shortages and scheduling. Furthermore, the infrastructure for hearing-impaired individuals to smoothly access services in their living environments, such as physical stores, is not adequately developed. As a result, hearing-impaired individuals face limitations in accessing information and struggle to participate in society.

[0489] 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.

[0490] In this invention, the server includes a receiving means for acquiring audio information, an analysis means for converting the audio information into text information, and a translation means for converting the text information into sign language gesture information. This makes it possible for hearing-impaired individuals to receive explanations from store staff in real time as visual information.

[0491] "Auditory information" refers to data obtained from the generation of sound, and includes acoustic signals, including human voices.

[0492] "Receiving means" refers to devices or technical means for receiving audio information from an external source.

[0493] "Textual information" refers to data in string format that is obtained by converting audio information.

[0494] "Analysis means" refers to devices or technical means for converting audio information into text information.

[0495] "Sign language action information" refers to action data in the form of sign language, which is derived from textual information.

[0496] "Translation means" refers to devices or technical means for converting textual information into sign language gesture information.

[0497] "Visual information" refers to data in which sign language gestures are visually represented, and is usually presented as video.

[0498] "Generation means" refers to devices or technical means for generating visual information from sign language movement information.

[0499] "Display means" refers to devices or technical means for displaying generated visual information.

[0500] A "communication device" is a device or technical means for sending generated visual information to an external device or system for display.

[0501] "Application devices" refer to the devices and applications used to operate a system in an actual usage environment.

[0502] To implement this invention, the system has three main components: a server, a terminal, and a user. The server performs core processing that analyzes voice information and generates sign language action information. Specifically, the server uses a microphone device to receive voice information and converts it into text information using speech recognition software. By using a generative AI model, which is a highly accurate natural language processing model, for speech recognition, the system converts speech into text in a natural way.

[0503] Next, the server converts the textual information into sign language gesture information. This uses a translation algorithm that takes into account the grammatical structure of sign language to generate consistent sign language gesture information. Based on this sign language gesture information, computer graphics software, acting as a generation method, generates visual information using a 3D model. This allows the user to understand sign language as visual information.

[0504] The terminal's role is to display visual information transmitted from the server on the user's device. Monitors or smart glasses are used as display means, presenting visual information in real time. The application device dynamically transmits the generated visual information to the user's device via a communication device.

[0505] For example, if a hearing-impaired person wants to learn more about a product in a physical store, the explanation from the store clerk is received as audio information via a microphone. The server converts the audio into text information, and then translates it into sign language gestures. Based on the accurate gesture information generated by the AI ​​model, a 3D animation is created and displayed in real time on smart glasses or similar devices.

[0506] As an example of a prompt, when the voice prompt "Where is this product manufactured?" is converted into sign language, a message such as "Please display a sign language description of the teacup's manufacturer" might be generated. This allows the user to obtain information in real time.

[0507] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0508] Step 1:

[0509] The system acquires voice information emitted by the user using the device's microphone. The input is an audio signal, which is encoded as a digital signal for transmission to the server. The output is the digitized audio information.

[0510] Step 2:

[0511] The server analyzes the digital audio information received from the terminal using a speech recognition module. The input is digital audio information, which is then converted into text information with high accuracy using a generative AI model. The output is natural language text information.

[0512] Step 3:

[0513] The server translates the generated text information into sign language action information. The input is text information, and a translation algorithm that considers the grammatical structure of sign language is applied. The output is sign language action information. During this process, prompts are used to instruct the server on how to generate the sign language.

[0514] Step 4:

[0515] The server generates 3D animations using a visual information generation module based on sign language motion information. The input is sign language motion information, and computer graphics technology is used to create visual animations. The output is visual information of a 3D model.

[0516] Step 5:

[0517] The terminal receives visual information transmitted from the server and displays it on a monitor or smart glasses. The input is visual information of a 3D model, which is presented on the display so that the user can visually receive sign language in real time. The output is sign language video that reaches the user's eyes.

[0518] 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.

[0519] The sign language interpretation system of the present invention not only converts speech into sign language images, but also incorporates a function to recognize the user's emotions and adjust the sign language expression accordingly. This provides more natural and emotionally rich sign language interpretation.

[0520] The voices that users produce during lectures or conversations are input into the system's microphone device. This audio data is digitized by the terminal, compressed, and then sent to the server.

[0521] The server uses speech recognition technology to analyze the audio data into text data. This process also includes an emotion engine that analyzes the tone and tempo of the speech to determine the user's emotional state (e.g., joy, sadness, anger).

[0522] The obtained text data is converted into sign language motion data by a translation tool, but the sign language motion data is also adjusted based on the emotional information recognized by the emotion engine. For example, if the user is expressing anger, the sign language motions will be expressed in a more exaggerated way.

[0523] The generation method generates 3D sign language images in real time based on adjusted sign language motion data. During this process, emotional expressions are also visually emphasized, enabling more natural and richer sign language interpretation.

[0524] Finally, the terminal receives the generated sign language video and displays it on a monitor or hologram device. In this way, the user can visually understand the audio information and the emotions it conveys with high accuracy. This system provides effective communication support for the hearing impaired in a variety of situations, for example, by conveying the emotions of a politician giving a speech in real time.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] The user speaks during a lecture or conversation, and the audio is input to the system via a microphone. The microphone collects the input audio as an analog signal.

[0528] Step 2:

[0529] The terminal converts the received analog audio signal into digital data. This digital data is compressed while maintaining sound quality and prepared for transmission to the server.

[0530] Step 3:

[0531] The terminal transmits compressed digital audio data to the server over the network. This process is performed quickly to enable real-time processing.

[0532] Step 4:

[0533] The server inputs the received audio data into the speech recognition engine and converts it into text data. In parallel, the emotion engine analyzes the pitch and intensity of the speech to determine the user's emotions.

[0534] Step 5:

[0535] The server uses the analyzed text data and emotional information to convert the text into sign language motion data using a translation mechanism. The emotional information influences the intensity and speed of the sign language movements, resulting in a more natural expression.

[0536] Step 6:

[0537] The server generates sign language videos using 3D animation technology based on sign language motion data. The generated videos have rich expressions that reflect emotions.

[0538] Step 7:

[0539] The server sends the generated sign language video to the terminal. The terminal decodes this data and prepares it for display in the optimal format.

[0540] Step 8:

[0541] The terminal displays sign language images in real time on a monitor or hologram device. This allows users to visually and accurately understand the content and emotions of lectures and conversations.

[0542] (Example 2)

[0543] 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."

[0544] Conventional sign language interpretation systems simply convert audio data into sign language, which has the problem of not being able to adequately express the speaker's emotions and other auditory information. Furthermore, the lack of real-time capabilities in generating sign language video can hinder sophisticated communication. This invention aims to solve these problems and provide natural and dynamic sign language interpretation that takes emotions into account.

[0545] 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.

[0546] In this invention, the server includes an analysis means for analyzing audio data into text data, an emotion analysis means for analyzing the tone and tempo of the audio to determine emotion, and an adjustment means for translating the text data into sign language motion data and adjusting the sign language motion data based on the emotion information. This makes it possible to generate natural sign language video in real time, taking into account the speaker's emotions.

[0547] "Audio data" refers to data that represents the voice information spoken by a user in digital format.

[0548] "Receiving means" refers to a device or function for acquiring audio data.

[0549] "Conversion means" refers to a process or device for converting an analog audio signal into a digital signal.

[0550] "Compression methods" refer to technologies used to compress audio data to reduce the amount of data and enable more efficient transmission.

[0551] "Analysis means" refers to the process or technology of analyzing audio data and converting it into text data.

[0552] "Emotion analysis methods" are technologies that analyze the tone and tempo of voice data to determine the user's emotions.

[0553] "Translation means" refers to the technology or process for converting text data into sign language action data.

[0554] "Adjustment means" refers to a technique or process for modifying sign language action data based on emotional information.

[0555] "Generation means" refers to technology or equipment for generating 3D sign language images in real time based on sign language motion data.

[0556] "Display means" refers to a device or function for visually displaying the generated sign language video.

[0557] The sign language interpretation system of the present invention is designed to convert user-generated speech into sign language video while simultaneously providing natural sign language expressions that take emotions into consideration.

[0558] The system's implementation primarily involves three elements: terminals, servers, and users. Audio information emitted by users during lectures or conversations is captured by a microphone device connected to the terminal. The terminal uses an A / D conversion chip to convert this audio data into a digital signal, and then improves the audio quality through a noise reduction filter.

[0559] The acquired digital audio data is compressed on the terminal, and compression algorithms such as MP3 or AAC are used to efficiently transmit it to the server. This compressed data is sent to the server via the internet or the corporate network.

[0560] On the server, a speech recognition engine converts speech data into text data. During this process, an emotion analysis engine operates, evaluating the speaker's tone and tempo to determine the user's emotional state. These analysis results are integrated into the process of translating the text data into sign language motion data using machine translation technology.

[0561] Sign language motion data is further refined based on emotional information, and a generative AI model is used to generate 3D sign language video in real time. This makes it possible to express sign language dynamically by emphasizing visual effects.

[0562] The terminal ultimately displays 3D sign language images received from the server via a display or hologram device. This system structure allows hearing-impaired individuals to visually understand information, including the emotions of speakers during lectures and conversations.

[0563] For example, when a user asks questions during a school lesson, it is possible to accurately visualize the excitement and anticipation conveyed in the student's question using sign language and communicate it to other participants.

[0564] An example of a prompt is, "Generate a sign language interpretation that takes into account the emotions of this speech." This prompt prompts the system to generate and display a sign language video that includes emotions based on the audio information.

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The user emits sound during a lecture or conversation. This sound is captured as an analog signal through a microphone device connected to the terminal. The terminal converts the analog audio signal into digital data using an A / D conversion chip. The input is an analog audio signal, and the output is digitized audio data.

[0568] Step 2:

[0569] The device processes digitized audio data using a compression algorithm to reduce its size. Specifically, it uses compression technologies such as MP3 and AAC. The input is digital audio data, and the output is compressed audio data.

[0570] Step 3:

[0571] Compressed audio data is sent from the terminal to the server. A communication line such as the internet or a LAN is used for data transfer. The input is compressed audio data, and the output is the server's reception status.

[0572] Step 4:

[0573] The server analyzes the received audio data using a speech recognition engine and converts it into text data. During this process, the content of the audio data is extracted as text information. The input is compressed audio data, and the output is text data.

[0574] Step 5:

[0575] The server uses an emotion analysis engine to analyze voice tone and tempo to estimate the user's emotions. Specific algorithms include phoneme analysis and intonation evaluation. The input is voice data, and the output is emotional information.

[0576] Step 6:

[0577] The server uses machine translation technology to convert text data into sign language motion data. During this process, emotional information is also integrated, and the sign language movements are adjusted to be more natural. The input is text data and emotional information, and the output is the adjusted sign language motion data.

[0578] Step 7:

[0579] The adjusted sign language motion data is converted into 3D sign language video in real time by the server's generated AI model. This enhances visual expression and enables richer sign language interpretation. The input is sign language motion data, and the output is 3D sign language video.

[0580] Step 8:

[0581] The terminal displays 3D sign language video received from the server on a hologram device or monitor. The user understands the audio content and emotions by visually receiving this video. The input is 3D sign language video, and the output is a visual display of the video.

[0582] (Application Example 2)

[0583] 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."

[0584] In providing communication support to users with hearing impairments, it is crucial to accurately convey not only the content of the spoken words but also the speaker's emotions and intentions. However, conventional sign language interpretation systems often fail to adequately reflect emotional expression, making natural and rich communication difficult.

[0585] 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.

[0586] In this invention, the server includes an acquisition means for acquiring acoustic data, an analysis means for converting the acoustic data into text data, and a translation means for converting the text data into sign language motion data and adjusting the sign language motion data based on the emotion analysis results. This makes it possible to reflect the user's emotions in sign language and enable natural and emotionally rich communication.

[0587] "Audio data" refers to information that represents speech or sound in digital format.

[0588] "Acquisition means" refers to a configuration that has the function of collecting acoustic data and inputting it into a digital device.

[0589] "Analysis means" refers to a device or function that performs the process of converting acquired acoustic data into text data.

[0590] "Text data" refers to information represented in text format, which is a conversion of speech into linguistic expression.

[0591] A "translation method" is a configuration that converts text data into sign language motion data and also has the function of adjusting the sign language motion data based on the results of emotion analysis.

[0592] "Sign language action data" refers to a series of data representing actions that indicate sign language expressions.

[0593] "Generation means" refers to a device or function that creates three-dimensional sign language video based on adjusted sign language motion data.

[0594] "Display means" refers to a device or apparatus that visually outputs the generated three-dimensional sign language video.

[0595] "Emotional analysis results" refer to information indicating the emotional state analyzed from acoustic data.

[0596] The system for realizing this application consists of a process that acquires acoustic data, analyzes emotions from the speech, and generates and displays three-dimensional sign language video. The details are shown below.

[0597] The server receives audio data acquired through smartphones or dedicated audio input devices. This audio data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). At the same time, an emotion analysis engine (e.g., IBM Watson Tone Analyzer) is used to generate emotion analysis results from the audio. Based on this emotion analysis, the translation system converts the text data into sign language gesture data and further adjusts it to reflect emotions.

[0598] Next, the generation means generates a three-dimensional sign language video in real time using the adjusted sign language motion data, and outputs it to the display means, i.e., the user's smartphone or a connected display.

[0599] For example, in a scene where a staff member at a nursing home cheerfully asks an elderly resident, "It's a nice day today, shall we go for a walk?", the server can interpret that emotion and add cheerful expressions to the sign language video. In this way, the elderly can gain a deeper understanding of the intentions and emotions behind the care staff's suggestion.

[0600] An example of a prompt for the generation AI model is, "Please reflect positive emotions from the audio data into the sign language video so that elderly people can understand it."

[0601] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0602] Step 1:

[0603] The user acquires audio data (sound) using a smartphone or a dedicated audio input device. The input is real-time audio data, and the output is digital audio data.

[0604] Step 2:

[0605] The terminal sends the acquired audio data to the server. The server inputs the received audio data into a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts it into text data. The input is audio data, and the output is text data. In this process, speech extraction and text conversion are performed using audio signal processing.

[0606] Step 3:

[0607] The server simultaneously uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the audio data. The input for this step is the audio data, and the output is the emotion analysis result. Elements such as tone, tempo, and emphasis are analyzed.

[0608] Step 4:

[0609] The server uses translation tools to convert text data and sentiment analysis results into sign language action data. Furthermore, it adjusts the sign language action data based on the sentiment analysis results. The input is text data and sentiment analysis results, and the output is the adjusted sign language action data.

[0610] Step 5:

[0611] The server uses a generation mechanism to generate three-dimensional sign language video in real time based on adjusted sign language motion data. The input is adjusted sign language motion data, and the output is three-dimensional sign language video. 3D modeling and animation generation are performed here.

[0612] Step 6:

[0613] The device receives the generated three-dimensional sign language video and displays it on the user's smartphone or a connected display. The input is three-dimensional sign language video, and the output is a visually displayed image. In this way, the user can visually understand the audio information and its emotions.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] The sign language interpretation system of the present invention provides information to the hearing impaired by displaying audio as sign language images in real time in situations such as lectures and meetings. This system includes receiving means, analysis means, translation means, generation means, and display means.

[0632] The user inputs sound data into the microphone device of the sign language interpretation system by making a sound. This sound data is converted into digital data by the terminal and sent to the server.

[0633] When the server receives this audio data, it analyzes it into text data using speech recognition technology. The speech recognition utilizes a highly accurate natural language processing model to precisely convert spoken content into text.

[0634] Next, the text data is converted into sign language movement data by a translation tool. The translation tool maintains information consistency by converting the text into appropriate sign language movements while considering the grammatical structure of sign language.

[0635] The generation method generates 3D model sign language videos based on sign language motion data. This generation method has the capability to create visually recognizable sign language animations in real time using computer graphics technology.

[0636] Ultimately, the device receives the generated sign language video and displays it on a monitor or hologram display. This allows the user to visually receive sign language in real time, improving the efficiency of communication.

[0637] This system eliminates the problem of sign language interpreter shortages and scheduling issues, enabling rapid sign language interpretation services in a variety of situations. For example, when experts present at academic conferences, hearing-impaired attendees can understand the presentation in real time. These advantages contribute to improving information access for the hearing impaired.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] When a user speaks, their voice is input through the system's microphone. The microphone receives the voice as an analog signal.

[0641] Step 2:

[0642] The terminal converts the analog audio signal from the microphone into digital data. After conversion, it compresses the digital audio data and prepares it for efficient transmission to the server.

[0643] Step 3:

[0644] The server receives the audio data transmitted from the terminal. The server analyzes the digital audio data using a speech recognition engine and converts it from audio to text data. This engine uses a language model to recognize even the finer details of pronunciation.

[0645] Step 4:

[0646] The server passes the obtained text data to a translation tool, which converts it into sign language action data. Translation is performed using sign language grammar rules and a dictionary database, aiming to preserve the meaning precisely.

[0647] Step 5:

[0648] The server generates 3D sign language videos based on translated sign language motion data. The generation method utilizes 3D animation technology to achieve dynamic expression of sign language movements.

[0649] Step 6:

[0650] The generated sign language video is sent from the server to the terminal. The compression technology used here minimizes streaming latency while maintaining high-quality video.

[0651] Step 7:

[0652] The terminal decodes the received sign language video and displays it on a monitor or hologram device. This allows users to visually receive sign language interpretation in real time and understand information efficiently.

[0653] (Example 1)

[0654] 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".

[0655] Conventional sign language interpretation systems sometimes lack sufficient accuracy and speed when converting audio to sign language video, resulting in inadequate information provision for the hearing impaired, particularly in lectures and conferences where real-time information is required. Furthermore, given the shortage of sign language interpreters and the difficulty in scheduling, there is a need for a system that can respond quickly.

[0656] 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.

[0657] In this invention, the server includes a conversion device that converts speech information into coded data, an analysis device that analyzes the coded data into character information, and a conversion device that converts the character information into visual language action data. This enables the generation of sign language videos in real time through high-precision speech analysis and rapid visual language conversion, making it possible to efficiently provide information to people with hearing impairments.

[0658] An "input device" is a device used to acquire voice information into a system.

[0659] A "conversion device" is a device used to convert acquired audio information into coded data or visual language action data.

[0660] An "analysis device" is a device that analyzes coded data and converts it into character information.

[0661] A "generation device" is a device that generates three-dimensional images based on visual language action data.

[0662] An "output device" is a device used to display the generated three-dimensional image to the user.

[0663] A "transmission device" is a device used to compress audio information and transmit it to other devices or systems.

[0664] A "three-dimensional model" is a data structure that represents digitally structured information in three dimensions and is used for visual representation.

[0665] This sign language interpretation system is designed to allow hearing-impaired individuals to receive audio information as sign language video in situations such as lectures and conferences. The specific implementation details are described below.

[0666] The user emits voice in a lecture hall or conference room. The voice information is acquired by an input device (e.g., a microphone) that the user possesses or that is placed in the venue. The acquired voice information is converted from an analog signal to digital data by a conversion device installed in the terminal for digital signal processing, and then transmitted to a server using a transmission device.

[0667] The server receives the transmitted digital audio data. The received data is converted into text information via an analysis device. This analysis utilizes highly accurate speech recognition technology and leverages a generative AI model to achieve high-precision text conversion. One example of a model that could be used is an open-source speech recognition API.

[0668] The converted text information is then converted into visual language action data by another conversion device on the server. This step takes into account the grammatical structure of sign language and processes the text data to accurately translate it into sign language action data. The conversion process implements a sign language-specific action dictionary database to ensure information consistency between languages.

[0669] Subsequently, the visual language action data is converted into a three-dimensional image on the server using a generation device that utilizes a three-dimensional model. The generated sign language image is rendered in real time and provided in a visually recognizable format. Advanced computer graphics software (e.g., Unity) can be used for this visualization.

[0670] The generated three-dimensional sign language video data is then transmitted to the terminal's output device. The terminal displays the video on a monitor or hologram display, allowing the user to visually receive the sign language information. As a result, hearing-impaired individuals can receive information in real time through sign language video, even in situations where audio information is being transmitted.

[0671] As a concrete example, let's consider real-time sign language interpretation at an academic conference. By inputting audio data from presentations at the conference into the system, people with hearing impairments can understand the content in real time. As an example of a prompt to the generative AI model, we can consider something like, "Please translate the content of the next presentation into sign language in real time."

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] The user inputs voice information into the system via an input device. Specifically, the user speaks into the microphone device. This operation acquires voice data in analog format.

[0675] Step 2:

[0676] The terminal converts analog audio data obtained from the input device into digital data. The conversion uses an AD converter in the conversion device. The input is analog audio, and the output is coded data in a digital format. This coded data is transmitted to the server in an optimized format for efficient processing.

[0677] Step 3:

[0678] The server receives coded data and converts it into character information using an analysis device. Specifically, it applies a speech recognition algorithm and utilizes a generative AI model to extract text. The input is coded data, and the output is analyzed character information. High-precision text conversion is achieved by utilizing natural language processing.

[0679] Step 4:

[0680] The server uses the analyzed textual information to convert it into visual language action data. A translation device is used to perform data conversion based on sign language grammar. The input is textual information, and the output is visual language action data corresponding to sign language. This process is carried out while maintaining the consistency of sign language expression.

[0681] Step 5:

[0682] The server generates three-dimensional images based on visual language action data. Using a generation device and advanced computer graphics technology, it renders sign language animations in real time. The input is action data, and the output is three-dimensional sign language video. This video is designed to be intuitively understandable to the user.

[0683] Step 6:

[0684] The terminal receives three-dimensional sign language video transmitted from the server and displays it using an output device. The video is displayed in real time on a monitor or hologram display. The input is three-dimensional video data, and the output is presented to the user as visual information. This allows people with hearing impairments to visually absorb information in lectures and meetings.

[0685] (Application Example 1)

[0686] 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".

[0687] Traditionally, hearing-impaired individuals have had to rely on sign language interpreters to obtain information, leading to problems with interpreter shortages and scheduling. Furthermore, the infrastructure for hearing-impaired individuals to smoothly access services in their living environments, such as physical stores, is not adequately developed. As a result, hearing-impaired individuals face limitations in accessing information and struggle to participate in society.

[0688] 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.

[0689] In this invention, the server includes a receiving means for acquiring audio information, an analysis means for converting the audio information into text information, and a translation means for converting the text information into sign language gesture information. This makes it possible for hearing-impaired individuals to receive explanations from store staff in real time as visual information.

[0690] "Auditory information" refers to data obtained from the generation of sound, and includes acoustic signals, including human voices.

[0691] "Receiving means" refers to devices or technical means for receiving audio information from an external source.

[0692] "Textual information" refers to data in string format that is obtained by converting audio information.

[0693] "Analysis means" refers to devices or technical means for converting audio information into text information.

[0694] "Sign language action information" refers to action data in the form of sign language, which is derived from textual information.

[0695] "Translation means" refers to devices or technical means for converting textual information into sign language gesture information.

[0696] "Visual information" refers to data in which sign language gestures are visually represented, and is usually presented as video.

[0697] "Generation means" refers to devices or technical means for generating visual information from sign language movement information.

[0698] "Display means" refers to devices or technical means for displaying generated visual information.

[0699] A "communication device" is a device or technical means for sending generated visual information to an external device or system for display.

[0700] "Application devices" refer to the devices and applications used to operate a system in an actual usage environment.

[0701] To implement this invention, the system has three main components: a server, a terminal, and a user. The server performs core processing that analyzes voice information and generates sign language action information. Specifically, the server uses a microphone device to receive voice information and converts it into text information using speech recognition software. By using a generative AI model, which is a highly accurate natural language processing model, for speech recognition, the system converts speech into text in a natural way.

[0702] Next, the server converts the textual information into sign language gesture information. This uses a translation algorithm that takes into account the grammatical structure of sign language to generate consistent sign language gesture information. Based on this sign language gesture information, computer graphics software, acting as a generation method, generates visual information using a 3D model. This allows the user to understand sign language as visual information.

[0703] The terminal's role is to display visual information transmitted from the server on the user's device. Monitors or smart glasses are used as display means, presenting visual information in real time. The application device dynamically transmits the generated visual information to the user's device via a communication device.

[0704] For example, if a hearing-impaired person wants to learn more about a product in a physical store, the explanation from the store clerk is received as audio information via a microphone. The server converts the audio into text information, and then translates it into sign language gestures. Based on the accurate gesture information generated by the AI ​​model, a 3D animation is created and displayed in real time on smart glasses or similar devices.

[0705] As an example of a prompt, when the voice prompt "Where is this product manufactured?" is converted into sign language, a message such as "Please display a sign language description of the teacup's manufacturer" might be generated. This allows the user to obtain information in real time.

[0706] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0707] Step 1:

[0708] The system acquires voice information emitted by the user using the device's microphone. The input is an audio signal, which is encoded as a digital signal for transmission to the server. The output is the digitized audio information.

[0709] Step 2:

[0710] The server analyzes the digital audio information received from the terminal using a speech recognition module. The input is digital audio information, which is then converted into text information with high accuracy using a generative AI model. The output is natural language text information.

[0711] Step 3:

[0712] The server translates the generated text information into sign language action information. The input is text information, and a translation algorithm that considers the grammatical structure of sign language is applied. The output is sign language action information. During this process, prompts are used to instruct the server on how to generate the sign language.

[0713] Step 4:

[0714] The server generates 3D animations using a visual information generation module based on sign language motion information. The input is sign language motion information, and computer graphics technology is used to create visual animations. The output is visual information of a 3D model.

[0715] Step 5:

[0716] The terminal receives visual information transmitted from the server and displays it on a monitor or smart glasses. The input is visual information of a 3D model, which is presented on the display so that the user can visually receive sign language in real time. The output is sign language video that reaches the user's eyes.

[0717] 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.

[0718] The sign language interpretation system of the present invention not only converts speech into sign language images, but also incorporates a function to recognize the user's emotions and adjust the sign language expression accordingly. This provides more natural and emotionally rich sign language interpretation.

[0719] The voices that users produce during lectures or conversations are input into the system's microphone device. This audio data is digitized by the terminal, compressed, and then sent to the server.

[0720] The server uses speech recognition technology to analyze the audio data into text data. This process also includes an emotion engine that analyzes the tone and tempo of the speech to determine the user's emotional state (e.g., joy, sadness, anger).

[0721] The obtained text data is converted into sign language motion data by a translation tool, but the sign language motion data is also adjusted based on the emotional information recognized by the emotion engine. For example, if the user is expressing anger, the sign language motions will be expressed in a more exaggerated way.

[0722] The generation method generates 3D sign language images in real time based on adjusted sign language motion data. During this process, emotional expressions are also visually emphasized, enabling more natural and richer sign language interpretation.

[0723] Finally, the terminal receives the generated sign language video and displays it on a monitor or hologram device. In this way, the user can visually understand the audio information and the emotions it conveys with high accuracy. This system provides effective communication support for the hearing impaired in a variety of situations, for example, by conveying the emotions of a politician giving a speech in real time.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The user speaks during a lecture or conversation, and the audio is input to the system via a microphone. The microphone collects the input audio as an analog signal.

[0727] Step 2:

[0728] The terminal converts the received analog audio signal into digital data. This digital data is compressed while maintaining sound quality and prepared for transmission to the server.

[0729] Step 3:

[0730] The terminal transmits compressed digital audio data to the server over the network. This process is performed quickly to enable real-time processing.

[0731] Step 4:

[0732] The server inputs the received audio data into the speech recognition engine and converts it into text data. In parallel, the emotion engine analyzes the pitch and intensity of the speech to determine the user's emotions.

[0733] Step 5:

[0734] The server uses the analyzed text data and emotional information to convert the text into sign language motion data using a translation mechanism. The emotional information influences the intensity and speed of the sign language movements, resulting in a more natural expression.

[0735] Step 6:

[0736] The server generates sign language videos using 3D animation technology based on sign language motion data. The generated videos have rich expressions that reflect emotions.

[0737] Step 7:

[0738] The server sends the generated sign language video to the terminal. The terminal decodes this data and prepares it for display in the optimal format.

[0739] Step 8:

[0740] The terminal displays sign language images in real time on a monitor or hologram device. This allows users to visually and accurately understand the content and emotions of lectures and conversations.

[0741] (Example 2)

[0742] 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".

[0743] Conventional sign language interpretation systems simply convert audio data into sign language, which has the problem of not being able to adequately express the speaker's emotions and other auditory information. Furthermore, the lack of real-time capabilities in generating sign language video can hinder sophisticated communication. This invention aims to solve these problems and provide natural and dynamic sign language interpretation that takes emotions into account.

[0744] 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.

[0745] In this invention, the server includes an analysis means for analyzing audio data into text data, an emotion analysis means for analyzing the tone and tempo of the audio to determine emotion, and an adjustment means for translating the text data into sign language motion data and adjusting the sign language motion data based on the emotion information. This makes it possible to generate natural sign language video in real time, taking into account the speaker's emotions.

[0746] "Audio data" refers to data that represents the voice information spoken by a user in digital format.

[0747] "Receiving means" refers to a device or function for acquiring audio data.

[0748] "Conversion means" refers to a process or device for converting an analog audio signal into a digital signal.

[0749] "Compression methods" refer to technologies used to compress audio data to reduce the amount of data and enable more efficient transmission.

[0750] "Analysis means" refers to the process or technology of analyzing audio data and converting it into text data.

[0751] "Emotion analysis methods" are technologies that analyze the tone and tempo of voice data to determine the user's emotions.

[0752] "Translation means" refers to the technology or process for converting text data into sign language action data.

[0753] "Adjustment means" refers to a technique or process for modifying sign language action data based on emotional information.

[0754] "Generation means" refers to technology or equipment for generating 3D sign language images in real time based on sign language motion data.

[0755] "Display means" refers to a device or function for visually displaying the generated sign language video.

[0756] The sign language interpretation system of the present invention is designed to convert user-generated speech into sign language video while simultaneously providing natural sign language expressions that take emotions into consideration.

[0757] The system's implementation primarily involves three elements: terminals, servers, and users. Audio information emitted by users during lectures or conversations is captured by a microphone device connected to the terminal. The terminal uses an A / D conversion chip to convert this audio data into a digital signal, and then improves the audio quality through a noise reduction filter.

[0758] The acquired digital audio data is compressed on the terminal, and compression algorithms such as MP3 or AAC are used to efficiently transmit it to the server. This compressed data is sent to the server via the internet or the corporate network.

[0759] On the server, a speech recognition engine converts speech data into text data. During this process, an emotion analysis engine operates, evaluating the speaker's tone and tempo to determine the user's emotional state. These analysis results are integrated into the process of translating the text data into sign language motion data using machine translation technology.

[0760] Sign language motion data is further refined based on emotional information, and a generative AI model is used to generate 3D sign language video in real time. This makes it possible to express sign language dynamically by emphasizing visual effects.

[0761] The terminal ultimately displays 3D sign language images received from the server via a display or hologram device. This system structure allows hearing-impaired individuals to visually understand information, including the emotions of speakers during lectures and conversations.

[0762] For example, when a user asks questions during a school lesson, it is possible to accurately visualize the excitement and anticipation conveyed in the student's question using sign language and communicate it to other participants.

[0763] An example of a prompt is, "Generate a sign language interpretation that takes into account the emotions of this speech." This prompt prompts the system to generate and display a sign language video that includes emotions based on the audio information.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The user emits sound during a lecture or conversation. This sound is captured as an analog signal through a microphone device connected to the terminal. The terminal converts the analog audio signal into digital data using an A / D conversion chip. The input is an analog audio signal, and the output is digitized audio data.

[0767] Step 2:

[0768] The device processes digitized audio data using a compression algorithm to reduce its size. Specifically, it uses compression technologies such as MP3 and AAC. The input is digital audio data, and the output is compressed audio data.

[0769] Step 3:

[0770] Compressed audio data is sent from the terminal to the server. A communication line such as the internet or a LAN is used for data transfer. The input is compressed audio data, and the output is the server's reception status.

[0771] Step 4:

[0772] The server analyzes the received audio data using a speech recognition engine and converts it into text data. During this process, the content of the audio data is extracted as text information. The input is compressed audio data, and the output is text data.

[0773] Step 5:

[0774] The server uses an emotion analysis engine to analyze voice tone and tempo to estimate the user's emotions. Specific algorithms include phoneme analysis and intonation evaluation. The input is voice data, and the output is emotional information.

[0775] Step 6:

[0776] The server uses machine translation technology to convert text data into sign language motion data. During this process, emotional information is also integrated, and the sign language movements are adjusted to be more natural. The input is text data and emotional information, and the output is the adjusted sign language motion data.

[0777] Step 7:

[0778] The adjusted sign language motion data is converted into 3D sign language video in real time by the server's generated AI model. This enhances visual expression and enables richer sign language interpretation. The input is sign language motion data, and the output is 3D sign language video.

[0779] Step 8:

[0780] The terminal displays 3D sign language video received from the server on a hologram device or monitor. The user understands the audio content and emotions by visually receiving this video. The input is 3D sign language video, and the output is a visual display of the video.

[0781] (Application Example 2)

[0782] 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".

[0783] In providing communication support to users with hearing impairments, it is crucial to accurately convey not only the content of the spoken words but also the speaker's emotions and intentions. However, conventional sign language interpretation systems often fail to adequately reflect emotional expression, making natural and rich communication difficult.

[0784] 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.

[0785] In this invention, the server includes an acquisition means for acquiring acoustic data, an analysis means for converting the acoustic data into text data, and a translation means for converting the text data into sign language motion data and adjusting the sign language motion data based on the emotion analysis results. This makes it possible to reflect the user's emotions in sign language and enable natural and emotionally rich communication.

[0786] "Audio data" refers to information that represents speech or sound in digital format.

[0787] "Acquisition means" refers to a configuration that has the function of collecting acoustic data and inputting it into a digital device.

[0788] "Analysis means" refers to a device or function that performs the process of converting acquired acoustic data into text data.

[0789] "Text data" refers to information represented in text format, which is a conversion of speech into linguistic expression.

[0790] A "translation method" is a configuration that converts text data into sign language motion data and also has the function of adjusting the sign language motion data based on the results of emotion analysis.

[0791] "Sign language action data" refers to a series of data representing actions that indicate sign language expressions.

[0792] "Generation means" refers to a device or function that creates three-dimensional sign language video based on adjusted sign language motion data.

[0793] "Display means" refers to a device or apparatus that visually outputs the generated three-dimensional sign language video.

[0794] "Emotional analysis results" refer to information indicating the emotional state analyzed from acoustic data.

[0795] The system for realizing this application consists of a process that acquires acoustic data, analyzes emotions from the speech, and generates and displays three-dimensional sign language video. The details are shown below.

[0796] The server receives audio data acquired through smartphones or dedicated audio input devices. This audio data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). At the same time, an emotion analysis engine (e.g., IBM Watson Tone Analyzer) is used to generate emotion analysis results from the audio. Based on this emotion analysis, the translation system converts the text data into sign language gesture data and further adjusts it to reflect emotions.

[0797] Next, the generation means generates a three-dimensional sign language video in real time using the adjusted sign language motion data, and outputs it to the display means, i.e., the user's smartphone or a connected display.

[0798] For example, in a scene where a staff member at a nursing home cheerfully asks an elderly resident, "It's a nice day today, shall we go for a walk?", the server can interpret that emotion and add cheerful expressions to the sign language video. In this way, the elderly can gain a deeper understanding of the intentions and emotions behind the care staff's suggestion.

[0799] An example of a prompt for the generation AI model is, "Please reflect positive emotions from the audio data into the sign language video so that elderly people can understand it."

[0800] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0801] Step 1:

[0802] The user acquires audio data (sound) using a smartphone or a dedicated audio input device. The input is real-time audio data, and the output is digital audio data.

[0803] Step 2:

[0804] The terminal sends the acquired audio data to the server. The server inputs the received audio data into a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts it into text data. The input is audio data, and the output is text data. In this process, speech extraction and text conversion are performed using audio signal processing.

[0805] Step 3:

[0806] The server simultaneously uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the audio data. The input for this step is the audio data, and the output is the emotion analysis result. Elements such as tone, tempo, and emphasis are analyzed.

[0807] Step 4:

[0808] The server uses translation tools to convert text data and sentiment analysis results into sign language action data. Furthermore, it adjusts the sign language action data based on the sentiment analysis results. The input is text data and sentiment analysis results, and the output is the adjusted sign language action data.

[0809] Step 5:

[0810] The server uses a generation mechanism to generate three-dimensional sign language video in real time based on adjusted sign language motion data. The input is adjusted sign language motion data, and the output is three-dimensional sign language video. 3D modeling and animation generation are performed here.

[0811] Step 6:

[0812] The device receives the generated three-dimensional sign language video and displays it on the user's smartphone or a connected display. The input is three-dimensional sign language video, and the output is a visually displayed image. In this way, the user can visually understand the audio information and its emotions.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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."

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] A receiving means for acquiring sound data,

[0837] An analysis means for converting the aforementioned sound data into text data,

[0838] A translation means for converting the aforementioned text data into sign language action data,

[0839] A generation means for generating sign language video based on the aforementioned sign language motion data,

[0840] A display means for displaying the aforementioned sign language video,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, further comprising a transmission means for compressing and transmitting the aforementioned sound data.

[0844] (Claim 3)

[0845] The system according to claim 1, comprising a generation means for generating the aforementioned sign language video in real time using a 3D model.

[0846] "Example 1"

[0847] (Claim 1)

[0848] An input device for acquiring audio information,

[0849] A conversion device that converts the aforementioned audio information into coded data,

[0850] An analysis device for analyzing the aforementioned coded data into character information,

[0851] A conversion device that converts the aforementioned character information into visual language action data,

[0852] A generation device that generates a three-dimensional image based on the aforementioned visual language action data,

[0853] The output device for displaying the three-dimensional image,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, further comprising a transmission device for compressing and transmitting the aforementioned audio information.

[0857] (Claim 3)

[0858] The system according to claim 1, comprising a generation device that generates the aforementioned three-dimensional image in real time using a three-dimensional model.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] A receiving means for acquiring audio information,

[0862] An analysis means for converting the aforementioned audio information into text information,

[0863] A translation means for converting the aforementioned textual information into sign language gesture information,

[0864] A generation means for generating visual information based on the aforementioned sign language motion information,

[0865] Display means for displaying the aforementioned visual information,

[0866] An application device that can dynamically present visual information via a communication device,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, further comprising a transmission means for reducing and transmitting the aforementioned audio information.

[0870] (Claim 3)

[0871] The system according to claim 1, comprising a generation means for instantly generating the aforementioned visual information using a three-dimensional model.

[0872] "Example 2 of combining an emotion engine"

[0873] (Claim 1)

[0874] A receiving means for acquiring audio data,

[0875] A conversion means for converting the aforementioned audio data into a digital signal,

[0876] A compression means for compressing the aforementioned audio data,

[0877] An analysis means for analyzing the aforementioned audio data into text data,

[0878] An emotion analysis means that analyzes the tone and tempo of the aforementioned audio data to determine the emotion,

[0879] A translation means for translating the aforementioned text data into sign language motion data,

[0880] An adjustment means for adjusting sign language action data based on the aforementioned emotional information,

[0881] A generation means for generating 3D sign language video in real time based on the aforementioned sign language motion data,

[0882] A display means for displaying the aforementioned sign language video,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, further comprising adjustment means for adjusting sign language motion data in consideration of the emotions in the voice data.

[0886] (Claim 3)

[0887] The system according to claim 1, comprising means for generating the aforementioned sign language video with added visual effects.

[0888] "Application example 2 when combining with an emotional engine"

[0889] (Claim 1)

[0890] Acquisition method for acquiring acoustic data,

[0891] An analysis means for converting the aforementioned acoustic data into character data,

[0892] A translation means that converts the aforementioned text data into sign language motion data and adjusts the sign language motion data based on the emotion analysis results,

[0893] A generation means for generating a three-dimensional sign language video based on the adjusted sign language motion data,

[0894] The display means for outputting the three-dimensional sign language video,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, further comprising a transmission means for compressing and transmitting the aforementioned acoustic data.

[0898] (Claim 3)

[0899] The system according to claim 1, having a function to adjust sign language movements based on the aforementioned emotion analysis. [Explanation of symbols]

[0900] 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 receiving means for acquiring sound data, An analysis means for converting the aforementioned sound data into text data, A translation means for converting the aforementioned text data into sign language action data, A generation means for generating sign language video based on the aforementioned sign language motion data, A display means for displaying the aforementioned sign language video, A system that includes this.

2. The system according to claim 1, further comprising a transmission means for compressing and transmitting the aforementioned sound data.

3. The system according to claim 1, comprising a generation means for generating the aforementioned sign language video in real time using a 3D model.

Images