Subtitle display method, subtitle system, computing device and readable storage medium

Abstract

The embodiment of the invention provides a subtitle display method, a subtitle system, computing equipment and a readable storage medium, the subtitle display method is applied to a server side of the subtitle system, and the subtitle system further comprises at least one display terminal. The method comprises the following steps: acquiring voice data collected from a target scene; performing voice text transcription on the voice data to obtain text data; packaging the text data to obtain network packet data; and distributing the network packet data to at least one display terminal through a data transmission interface corresponding to the at least one display terminal, so that each display terminal generates and displays subtitle data of the target scene based on text data in the network packet data. The calculation burden of the display terminal is relieved, the subtitle generation and display delay is remarkably reduced, the user experience is improved, the overall performance and expansibility of the system are improved, and the subtitle display reliability and stability are improved.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of multimedia technology, and more particularly to a subtitle display method, a subtitle system, a computing device, and a readable storage medium. Background Art

[0002] With the development of multimedia technology, real-time subtitle generation and display has been widely used in various scenarios, such as online teaching scenarios, news broadcasting and television scenarios, sports live scenarios, remote conferences, live art performances scenarios, etc.

[0003] At present, after acquiring the voice data collected from the field scene, the voice-to-text transcription is directly performed on the display terminal to obtain the text data, a subtitle layer is added to the scene screen, the text data is rendered on the subtitle layer, and a screen containing subtitles is generated for display.

[0004] However, since the transcription process of voice data is completed on the display terminal, the display terminal needs to undertake the additional calculation task of voice-to-text in addition to generating subtitle data. This will consume a lot of computing resources and may cause device performance to decline, resulting in a long delay in the entire subtitle generation and display, affecting the user experience. Moreover, when displaying subtitle data on at least one display terminal, each display terminal needs to independently complete the calculation task of voice transcription text, which increases the complexity and cost of subtitle display. Summary of the invention

[0005] In view of this, an embodiment of the present specification provides a subtitle display method. One or more embodiments of the present specification also relate to another subtitle display method, a subtitle system, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0006] According to a first aspect of an embodiment of the present specification, a subtitle display method is provided, which is applied to a server of a subtitle system, wherein the subtitle system further includes at least one display terminal; the method includes: Acquire speech data collected from a target scene; Performing voice-to-text transcription on the voice data to obtain text data; Encapsulate text data to obtain network packet data; The network packet data is distributed to at least one display terminal through a data transmission interface corresponding to at least one display terminal, so that each display terminal generates and displays subtitle data of a target scene based on text data in the network packet data.

[0007] According to a second aspect of an embodiment of the present specification, another subtitle display method is provided, which is applied to a first display terminal of a subtitle system, where the first display terminal is any one of at least one display terminal in the subtitle system, and the subtitle system further includes a server; the method includes: Receiving network packet data sent by the server through a data transmission interface corresponding to at least one display terminal, wherein the network packet data is obtained by encapsulating text data, the text data is obtained by transcribing voice data into text, and the voice data is collected from the target scene; Parse network packet data to obtain text data; Based on the text data, subtitle data of the target scene is generated and displayed.

[0008] According to a third aspect of the embodiments of this specification, a subtitle system is provided, including a server and at least one display terminal, the server including an audio processor, a voice transcription server, and a unified management platform server, and a data transmission interface corresponding to the at least one display terminal is a full-duplex transmission interface corresponding to the at least one display terminal preset on the unified management platform server; An audio processor, used to pre-process the voice data collected by the acquisition device from the target scene to obtain pre-processed voice data, wherein the pre-processing includes but is not limited to: at least one of noise reduction, volume standardization, removal of silence segments, echo cancellation, and format conversion; A voice transcription server is used to transcribe the voice data into text to obtain text data; The unified management platform server is used to encapsulate the text data using a full-duplex transmission protocol to obtain network packet data, and distribute the network packet data to at least one display terminal through a full-duplex transmission interface corresponding to at least one display terminal; At least one display terminal is used to receive network packet data sent by the server, parse the network packet data, obtain text data, and generate and display subtitle data of the target scene based on the text data.

[0009] According to a fourth aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above method are implemented.

[0010] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and the steps of the above method are implemented when the computer program / instruction is executed by a processor.

[0011] According to a sixth aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0012] A subtitle display method provided by an embodiment of the present specification is applied to the server side of a subtitle system, and the subtitle system also includes at least one display terminal; the method includes: acquiring voice data collected from a target scene; performing voice-to-text transcription on the voice data to obtain text data; encapsulating the text data to obtain network packet data; and distributing the network packet data to at least one display terminal through a data transmission interface corresponding to at least one display terminal, so that each display terminal generates and displays subtitle data of the target scene based on the text data in the network packet data.

[0013] By concentrating the computational tasks of voice-to-text conversion on the server side, the computational burden on the display terminal is reduced, the delay in subtitle generation and display is significantly reduced, the user experience is improved, the complexity and cost of each terminal independently completing voice transcription is avoided, and the overall performance and scalability of the system are improved. In addition, at least one data transmission interface corresponding to a display terminal is preset on the server side to ensure that the server side can efficiently and reliably distribute network packet data to each display terminal, thereby improving the reliability and stability of subtitle display. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of a subtitle display method provided by an embodiment of this specification; Figure 2 It is a flowchart of a processing process of a subtitle display method provided by an embodiment of this specification applied to a teaching scenario; Figure 3 is a flowchart of another subtitle display method provided by an embodiment of this specification; Figure 4 It is a display schematic diagram of another subtitle display method provided by an embodiment of this specification applied to a teaching scene; Figure 5 is a structural diagram of a subtitle system provided by an embodiment of this specification; Figure 6 It is a flowchart of a subtitle system provided by an embodiment of this specification; Figure 7 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0015] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0016] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0017] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0018] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0019] First, the terms involved in one or more embodiments of this specification are explained.

[0020] Automatic Speech Recognition (ASR): A technology that transcribes speech data into text data by analyzing its speech features.

[0021] Mel-Frequency Cepstral Coefficients (MFCC): A commonly used method for extracting speech signal features, used to convert speech signals into a set of coefficients that can reflect their spectral characteristics. MFCC simulates the human ear's perception of different frequencies, and reduces the impact of high-frequency components by mapping frequencies to the Mel scale, thereby better capturing the important features of speech signals. MFCC is widely used in automatic speech recognition and other speech processing tasks.

[0022] Linear Predictive Coding (LPC): A technique used in speech signal processing that represents speech signals by predicting the value of the current sample point. LPC analyzes the autocorrelation characteristics of speech signals and establishes a linear prediction model to extract a set of parameters that can describe speech signals. LPC has important applications in speech coding, speech synthesis, and automatic speech recognition.

[0023] Fourier Transform (FT) is a mathematical transformation technique used to convert time domain signals into frequency domain signals. Fast Fourier Transform (FFT) is an efficient algorithm for Fourier Transform that can quickly calculate Discrete Fourier Transform (DFT). FT is widely used in signal processing, image processing, communication systems and other fields, especially in the spectrum analysis of speech signals.

[0024] Hidden Markov Model (HMM): A statistical model used to model time series data, especially in speech recognition and natural language processing. HMM assumes that the state of the system at a certain moment depends only on the state at the previous moment, and describes the dynamic behavior of the system through state transition probabilities and observation probabilities. HMM is often used to model the time series characteristics of speech signals in automatic speech recognition.

[0025] Deep Neural Network (DNN): A multi-layer neural network that learns complex features of input data through multiple hidden layers. DNN can automatically extract high-level abstract features and has strong nonlinear modeling capabilities. DNN has achieved remarkable results in image recognition, speech recognition, natural language processing and other fields. In particular, in automatic speech recognition, DNN can significantly improve the accuracy and robustness of recognition.

[0026] Convolutional Neural Network (CNN): A deep learning model specifically designed to process data with a grid structure (such as images and speech signals). CNN can effectively extract local features and spatial relationships through structures such as convolutional layers, pooling layers, and fully connected layers. CNN performs well in areas such as image recognition, speech recognition, and natural language processing. In particular, in feature extraction of speech signals, CNN can capture local time-frequency features.

[0027] Recurrent Neural Network (RNN): A neural network used to process time series data that can capture the temporal dependencies of input data. RNN introduces recurrent connections in the hidden layer, allowing the network to remember previous input information, giving it an advantage in processing sequence data. RNN is widely used in tasks such as natural language processing, speech recognition, and time series prediction, especially variants such as Long Short Term Memory (LSTM) and Gate Recurrent Unit (GRU), which can effectively solve long-term dependency problems.

[0028] Deep Attention Model (Transformer Model): A deep learning model for natural language processing tasks, proposed by Google in 2017. The Transformer model abandons the traditional recurrent neural network (RNN) structure and is completely based on the attention mechanism. It can process all elements in the input sequence in parallel, significantly improving the efficiency and performance of processing long sequence data. The Transformer model performs well in tasks such as machine translation, text generation, and question-answering systems.

[0029] Bidirectional Encoder Representations from Transformers (BERT model): A pre-trained language model. BERT uses a bidirectional Transformer encoder structure to simultaneously consider contextual information and generate richer word embedding representations. The BERT model significantly improves the performance of natural language understanding tasks through large-scale unsupervised pre-training and task-specific fine-tuning, and is widely used in tasks such as text classification, named entity recognition, and sentiment analysis.

[0030] Generative Pre-trained Transformer (GPT model): A series of pre-trained language models. The GPT model is based on the Transformer architecture and generates high-quality text through large-scale unsupervised pre-training. The GPT model can generate coherent and natural text and is widely used in tasks such as text generation, dialogue systems, and machine translation.

[0031] Transmission Control Protocol / Internet Protocol (TCP / IP): A set of protocols used for Internet communications that defines how data is transmitted and routed in the network. TCP is responsible for reliable data transmission, ensuring the integrity and order of data packets through sequence numbers and acknowledgment numbers; IP is responsible for addressing and routing data packets, ensuring that data packets can reach the destination address from the source address.

[0032] Hypertext Transfer Protocol (HTTP): An application layer protocol used to transfer hypertext data between web browsers and web servers. It defines the message format of requests and responses and supports multiple methods (such as GET and POST) to request and transfer data.

[0033] File Transfer Protocol (FTP): A standard protocol for transferring files over the Internet. It allows users to upload and download files, supports a variety of commands to manage files and directories, and is often used for website management and file sharing.

[0034] Simple Mail Transfer Protocol (SMTP): A protocol for sending emails. It defines the rules and processes for transferring emails from the sender's mail server to the receiver's mail server, and supports reliable transmission and routing of emails.

[0035] WebSocket: A full-duplex transmission protocol that allows two-way communication between the client and the server. It enables real-time data exchange through a persistent connection and is often used in real-time chat, online games, and real-time data push.

[0036] Stream Control Transmission Protocol (SCTP): A message-oriented transport layer protocol that supports multi-stream and full-duplex transmission. It provides higher reliability and performance than TCP and is suitable for scenarios that require high reliability and high performance, such as telecommunications networks and real-time multimedia transmission.

[0037] In this specification, a subtitle display method is provided. One or more embodiments of this specification also relate to another subtitle display method, a subtitle system, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0038] See also Figure 1 , Figure 1 A flowchart of a subtitle display method provided according to an embodiment of the present specification is shown. The method is applied to a server of a subtitle system. The subtitle system also includes at least one display terminal, and includes the following specific steps: Step 102: Acquire speech data collected from the target scene.

[0039] A subtitle system is a network system used to transcribe speech data into text data and generate subtitle data based on the text data for display on multimedia data. A subtitle system usually consists of a server and multiple display terminals. For example, it can be widely used in online teaching, news broadcasting, sports live broadcasting, remote conferences, live art performances and other fields.

[0040] The server of the subtitle system is a network end in the subtitle system for receiving voice data, performing voice transcription and text processing, and packaging and distributing text data to the display terminal. The display terminal is a network end in the subtitle system for receiving network packet data, generating and displaying subtitle data of the target scene based on text data, including but not limited to at least one of the following: smart phones, tablet computers, personal computers, smart TVs, smart screens, etc.

[0041] The target scene is a real-world environment where subtitle data needs to be generated and displayed. Any environment where real-world speech data needs to be converted into visual text can be used as a target scene. For example, online teaching scenes, news broadcasting and television scenes, sports live scenes, remote conference scenes, live art performance scenes, etc.

[0042] Voice data is natural language audio data collected from the target scene. Voice data usually contains natural language audio of people, and may also contain non-natural language audio such as background sound and music. After being digitized, the voice data is sent to the server of the subtitle system for further processing. For example, in an online teaching, the teacher's explanation sound is collected by a microphone and converted into voice data in digital format.

[0043] In an optional embodiment of the present specification, the target scene includes a teaching scene.

[0044] Teaching scenarios are environments involving knowledge transfer and learning activities, including but not limited to traditional classrooms, online education platforms, and distance learning video conferences. In teaching scenarios, lecturers or teachers impart knowledge to students through oral explanations, demonstrations, etc. In order to improve learning efficiency and accessibility, the subtitle system can transcribe the lecturer's speech into text in real time and generate subtitles to help hearing-impaired students or non-native learners better understand the course content.

[0045] An optional way to obtain the voice data collected from the target scene is to obtain the voice data collected by the collection device in the target scene.

[0046] For example, in an online teaching scenario, a mathematics teacher conducts educational activities in the classroom, focusing on the blackboard: "Graphic definition and properties of quadratic functions ----------------------- 1. Definition: -General form: y = ax^2 + bx + c (a ≠ 0) -Standard form: y = a (xh) ^ 2 + k 2. Image: -parabola -Opening direction: a>0 upward, a<0 ​​downward -Vertex coordinates: (h, k) or (-b / 2a, f(-b / 2a)) 3. Nature: -Symmetry axis: x=-b / 2a -Zero point: Solve the equation ax^2+bx+c=0 -Discriminant Δ=b^2-4ac -Δ>0: two different real roots -Δ=0: a real root (repeated root) -Δ<0: no real roots 4. Application: -Physics: Parabolic Motion" is explained.

[0047] The teacher's voice data is collected through the microphone in the classroom: "Today we are going to learn the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions."

[0048] Acquire speech data collected from the target scene to provide speech data support for subsequent speech-to-text transcription.

[0049] In an optional embodiment of the present specification, before step 104, the following specific steps are also included: The voice data is preprocessed to obtain preprocessed voice data, wherein the preprocessing includes but is not limited to: at least one of noise reduction, volume normalization, removal of silence segments, echo cancellation, and format conversion.

[0050] Preprocessing is an optimization operation for voice data. The purpose of preprocessing is to improve the quality of voice data, reduce noise interference, ensure the clarity of voice data, and thus improve the accuracy and efficiency of voice transcription. Preprocessing includes but is not limited to: at least one of noise reduction, volume normalization, removal of silent segments, echo cancellation, and format conversion.

[0051] Noise reduction is the process of removing background noise from speech data to improve speech clarity. Noise reduction can effectively reduce the impact of environmental noise on speech quality, making speech data purer and helping to improve the accuracy of subsequent speech transcription. Noise reduction can be achieved using technologies such as spectral subtraction, adaptive filters, and deep learning models. For example, in a live sports broadcast, the commentator's voice is disturbed by the cheers and background music on the scene. Through noise reduction processing, these background noises can be removed, making the commentator's voice clearer.

[0052] Volume normalization is to adjust the volume of voice data to a uniform level to ensure that the volume of all voice segments is consistent. Volume normalization can avoid voice recognition errors caused by excessive volume fluctuations, making voice data more stable and reliable when processing. Volume normalization can be achieved using technologies such as automatic gain control (AGC) and dynamic range compression (DRC). For example, in a remote meeting, the volume of different speakers varies greatly, with some speakers speaking loudly and others speaking softly. Through volume normalization, the volume of all speakers can be kept consistent.

[0053] Removing silence segments is to remove the silent parts without voice activity from the voice data to reduce the amount of data and improve processing efficiency. Removing silence segments can reduce unnecessary data transmission and processing time, making the process of voice transcription more efficient. Removing silence segments can be achieved by using technologies such as energy threshold detection and short-time energy analysis. For example, in an online teaching, the teacher will have a short pause or thinking time during the explanation. By removing silence segments, these meaningless silent parts can be deleted, making the voice data more compact and efficient.

[0054] Echo cancellation is to remove the echo caused by sound wave reflection from the voice data to improve the clarity of the voice. Echo cancellation technology can effectively solve the echo problem caused by sound wave reflection in certain environments (such as large rooms or open spaces), making the voice data clearer and more natural. Echo cancellation can be achieved by using technologies such as adaptive filters and acoustic echo cancellation algorithms (AEC). For example, in a remote meeting, the reflection of the walls of the conference room causes obvious echoes in the speaker's voice. Through echo cancellation processing, these echoes can be removed to make the speaker's voice clearer.

[0055] Format conversion is to convert voice data from one audio data format to another audio data format to meet different processing and transmission requirements. Format conversion can ensure that voice data can be smoothly transmitted and processed between the various component units of the subtitle system, and improve the compatibility and flexibility of the subtitle system. Format conversion can be achieved using technologies such as audio codecs (such as LAME, FFmpeg), audio format conversion tools, etc. For example, in a news broadcast, the collected voice data may be in WAV format, but the server of the subtitle system may only support MP3 format. Through format conversion, the voice data in WAV format can be converted to MP3 format to ensure that the server can process the data smoothly.

[0056] The preprocessed speech data is the natural language audio data obtained through preprocessing. The preprocessed speech data usually mainly contains human natural language audio, and may also contain a small amount of non-natural language audio such as background sound and music. Compared with the original speech data, it has higher clarity and quality.

[0057] For example, for the teacher's voice data collected in the classroom: "Today we are going to learn the image and properties of quadratic functions. First, let's look at the definition of quadratic functions", the preprocessing operations of noise reduction, volume normalization, removal of silence segments, and echo cancellation are performed in sequence to obtain the preprocessed voice data.

[0058] By preprocessing the voice data, the quality of the voice data is significantly improved, and the accuracy and efficiency of subsequent voice transcription are improved.

[0059] Step 104: transcribe the speech data into text to obtain text data.

[0060] Text data is natural language text data obtained by transcribing voice data. Text data is a written text expression of voice data, which is used to display in multimedia in the form of subtitle data to help viewers better understand and obtain information. For example, in an online teaching, the teacher's explanation sound is collected by a microphone and converted into digital voice data, which is then transcribed into text data.

[0061] Speech-to-text transcription is the processing operation of converting natural language audio data into natural language text data, which can be achieved using technologies such as automatic speech recognition and natural language models.

[0062] For example, the teacher's voice data is: "Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions." The voice data is transcribed into text, and the text data obtained is: Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0063] The voice data is transcribed into text to obtain text data, which provides data support for subsequent packaging to obtain network packet data. In addition, the computing burden of the display terminal is reduced by concentrating the computing task of voice-to-text conversion on the server side.

[0064] In an optional embodiment of the present specification, step 104 includes the following specific steps: Automatic speech recognition technology is used to transcribe speech data into text to obtain text data.

[0065] Automatic speech recognition technology is a technology that transcribes speech data into text data by analyzing the speech features of speech data. Automatic speech recognition technology usually includes the following main steps: 1. Feature extraction: Extract acoustic features from speech data, such as Mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC), Fourier transform (FT), etc. 2. Acoustic model: Use acoustic models (such as HMM, DNN, CNN, RNN, etc.) to map acoustic features to the probability distribution of phonemes or words. 3. Decoding: Based on the probability distribution of phonemes or words, determine the word sequence with a high probability.

[0066] For example, the teacher's speech data is: "Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions." First, use the Mel spectrum cepstral coefficient to extract acoustic features from the speech data, and then use the HMM acoustic model to map the acoustic features to the probability distribution of phonemes or words. Based on the probability distribution of phonemes or words, determine the word sequence with high probability, and transcribe the text data: Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0067] Automatic speech recognition technology is used to capture the acoustic features of speech data to complete speech-to-text transcription, thereby improving the efficiency and accuracy of speech-to-text transcription.

[0068] In an optional embodiment of the present specification, step 104 includes the following specific steps: The natural language model is used to transcribe the speech data into text to obtain text data.

[0069] A natural language model is a crossbow learning model that can understand and generate natural language text data. These models can predict the probability of the next word based on the input audio data and generate coherent text data by learning a large amount of sample audio data and the corresponding sample text data. Natural language models include but are not limited to: Transformer model, BERT model, GPT model, etc.

[0070] For example, the teacher's voice data is: "Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions." The above voice features are embedded encoded and input into the GPT model to perform voice-to-text transcription on the voice data to obtain text data: Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0071] Using a natural language model to complete speech-to-text transcription captures the language features of speech data to complete speech-to-text transcription, thereby improving the efficiency and accuracy of speech-to-text transcription.

[0072] Step 106: Encapsulate the text data to obtain network packet data.

[0073] Network packet data is a data transmission unit encapsulated according to the network protocol. The network packet data includes the text data to be transmitted and the control information corresponding to the network protocol. The control information includes the rule information of the network protocol (format, check code, type of network data packet, flag, sequence number, confirmation number, etc.) and transmission information (for example, source address, destination address, port number, etc.). The control information ensures that the data can be correctly and securely transmitted from the server to the display terminal.

[0074] Encapsulating the text data to obtain network packet data, an optional way is: utilizing a network protocol to encapsulate the text data to obtain network packet data.

[0075] Among them, network protocols define the rules and standards for how network packet data is transmitted in the network, for example, TCP / IP, HTTP, FTP, SMTP, WebSocket, SCTP, etc.

[0076] For example, we use the network protocol to encapsulate text data (today we are going to learn the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions) to obtain network packet data: 0x81 0x36 0xe4 0xbd 0xa0 0xe4 0xbd 0xa0 0xe8 0xa6 0x81 0xe5 0xad 0xab0xe7 0x9a 0x84 0xe6 0x98 0xaf 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe50x87 0xa0 0xe7 0x9a 0x84 0xe5 0x9b 0xbe 0xe5 0x83 0x8f 0xe5 0x92 0x8c 0xe60x80 0xa7 0xe8 0xb4 0xa8 0xe3 0x80 0x82 0xe9 0xa6 0x96 0xe5 0x85 0xa8 0xe60x88 0x91 0xe4 0xbb 0xac 0xe6 0x9d 0xa5 0xe7 0x9c 0x8b 0xe4 0xb8 0x80 0xe40xba 0b 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe7 0x9a 0x84 0xe5 0xae 0x9a0xe4 0xb9 0x89 0xe3 0x80 0x82.

[0077] By encapsulating the text data, network packet data is obtained, which provides data support for the subsequent server to efficiently and reliably distribute the network packet data to various display terminals.

[0078] In an optional embodiment of the present specification, step 106 includes the following specific steps: The full-duplex transmission protocol is used to encapsulate the text data to obtain network packet data.

[0079] Full-duplex transmission protocols are communication protocols that allow data to be transmitted in both directions at the same time, for example, WebSocket, SCTP. Compared with half-duplex protocols, full-duplex protocols can send and receive data at the same time, thereby improving the efficiency of data transmission and bandwidth utilization. Full-duplex transmission protocols are very useful in scenarios that require high-speed, two-way communication, such as real-time video calls, online conferences, real-time subtitle systems, etc. Full-duplex transmission protocols usually rely on the support of underlying hardware, such as physical layer technologies such as Ethernet and Wi-Fi.

[0080] For example, the WebSocket protocol is used to encapsulate text data (today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions) to obtain network packet data: 0x81 0x36 0xe4 0xbd 0xa0 0xe4 0xbd 0xa0 0xe8 0xa6 0x81 0xe5 0xad 0xab0xe7 0x9a 0x84 0xe6 0x98 0xaf 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe50x87 0xa0 0xe7 0x9a 0x84 0xe5 0x9b 0xbe 0xe5 0x83 0x8f 0xe5 0x92 0x8c 0xe60x80 0xa7 0xe8 0xb4 0xa8 0xe3 0x80 0x82 0xe9 0xa6 0x96 0xe5 0x85 0xa8 0xe60x88 0x91 0xe4 0xbb 0xac 0xe6 0x9d 0xa5 0xe7 0x9c 0x8b 0xe4 0xb8 0x80 0xe40xba 0b 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe7 0x9a 0x84 0xe5 0xae 0x9a0xe4 0xb9 0x89 0xe3 0x80 0x82.

[0081] Among them, 0x81: FIN=1 (last frame bit, indicating that this is the last frame of the message), RSV1=0, RSV2=0, RSV3=0 (reserved bit), Opcode=0x1 (text frame).

[0082] 0x36: MASK=0 (mask bit, indicating that mask is not used), Payload Length=54 (payload data length bit, indicating that the length of the text content is 54).

[0083] 0xe4 0xbd 0xa0 ... 0xe3 80 0x82: actual payload data, i.e. "Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions." The full-duplex transmission protocol is used to encapsulate network packet data, realize instant communication between the server and each display terminal, generate and display subtitle data in real time, significantly improve the response speed and reliability of the subtitle system, allow data to be transmitted in two directions simultaneously, reduce transmission delays, and ensure the real-time and accuracy of subtitle data.

[0084] Step 108: Distribute the network packet data to at least one display terminal through a data transmission interface corresponding to the at least one display terminal, so that each display terminal generates and displays subtitle data of the target scene based on the text data in the network packet data.

[0085] The data transmission interface corresponding to the display terminal is pre-set on the server side of the subtitle system to realize data transmission between the server side and each display terminal. These data transmission interfaces are used to efficiently and reliably transmit the network packet data generated by the server side to each display terminal, ensuring that the display terminal can receive and process these data, generate and display subtitles. The data transmission interface usually supports the network protocol that encapsulates the network packet data.

[0086] The subtitle data of the target scene is text data displayed on the multimedia data, with corresponding style and position information. Among them, the subtitle data can have different styles, such as font size, color, background color, transparency, etc., to adapt to different display requirements and audience preferences. Subtitle data can be displayed at a specified location on the multimedia data, such as the bottom, top or other specific areas of the screen to ensure that important content is not blocked. Subtitle data is a visual text content generated by transcribing the voice data collected in the target scene, which is used to assist the audience to better understand and obtain information. For example, in an online teaching, the teacher's explanation sound is collected by a microphone and converted into voice data in digital format. The voice data is transmitted to the server of the subtitle system to generate subtitle data for real-time display.

[0087] For example, the data transmission interfaces corresponding to the three display terminals, namely, a smart phone, a tablet computer and a smart screen, are: Smartphone: Interface name: MobileWebSocketInterface; Protocol: WebSocket; Function: used to establish a full-duplex connection with a smartphone and transmit network packet data in real time.

[0088] Tablet computer: Interface name: TabletSCTPInterface; Protocol: WebSocket; Function: used to establish a full-duplex connection with the tablet computer and transmit network packet data in real time.

[0089] Smart screen: Interface name: SmartScreenHTTPInterface; Protocol: WebSocket; Function: used to establish a full-duplex connection with the smart screen and transmit network packet data in real time.

[0090] Through these three interfaces, the network packet data is distributed to three display terminals. On these three display terminals, based on the text data in the network packet data (today we are going to learn the image and properties of quadratic functions. First, let's look at the definition of quadratic functions), subtitle data with corresponding style and position information in the online teaching scenario is generated and displayed: Smartphone: Style: Font size 18px, color white, background color black, transparency 80%; Position: bottom of the screen, 20px from the bottom edge; Display effect: Display subtitles at the bottom of the video screen: "Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions." Tablet computer: Style: Font size 22px, color white, background color dark gray, transparency 70%; Position: bottom of the screen, 30px from the bottom edge; Display effect: Display subtitles at the bottom of the video screen: "Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions." Smart screen: Style: Font size 30px, color yellow, background color black, transparency 60%; Position: bottom of the screen, 50px from the bottom edge; Display effect: Display subtitles at the bottom of the video screen: "Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions." In the embodiments of this specification, by concentrating the computational tasks of voice-to-text conversion on the server, the computational burden of the display terminal is reduced, the delay of subtitle generation and display is significantly reduced, the user experience is improved, the complexity and cost of each display terminal independently completing voice transcription is avoided, and the overall performance and scalability of the subtitle system are improved. In addition, at least one data transmission interface corresponding to the display terminal is preset on the server to ensure that the server can efficiently and reliably distribute network packet data to each display terminal, thereby improving the reliability and stability of subtitle display.

[0091] In an optional embodiment of the present specification, the server includes a unified management platform server, and the data transmission interface corresponding to at least one display terminal is a full-duplex transmission interface corresponding to at least one display terminal preset on the unified management platform server.

[0092] The unified management platform server is used to manage and coordinate the operation of the subtitle system. The unified management platform server centrally processes the transcription results of voice data and distributes the generated network packet data to each display terminal through a preset data transmission interface to ensure the real-time and accuracy of subtitle data. The unified management platform server centrally processes the transcription results of voice data and completes efficient and reliable data distribution to ensure that each terminal can receive and display subtitle data.

[0093] The full-duplex transmission interface corresponding to the display terminal is pre-set on the unified management platform server and is used for data transmission between the server and each display terminal. The full-duplex transmission interface supports full-duplex transmission protocols, such as WebSocket and SCTP, allowing data to be transmitted in two directions at the same time, thereby improving data transmission efficiency and bandwidth utilization.

[0094] By setting up a unified management platform server on the server side and presetting a full-duplex transmission interface corresponding to at least one display terminal on the unified management platform server, the real-time performance and reliability of the subtitle system are significantly improved. The unified management platform server centrally handles the transcription task of voice data, which reduces the computing burden of the display terminal and reduces the delay in subtitle generation and display. The full-duplex transmission interface ensures that data is efficiently and reliably transmitted to each display terminal, supports multiple terminals to receive and display subtitle data at the same time, and improves the overall performance of the system and user experience. In addition, this architecture also enhances the scalability and flexibility of the subtitle system, making it easier to add more display terminals and functional modules in the future.

[0095] At present, the commonly used subtitle display mode in smart classrooms is to directly display the voice transcription subtitles in the teaching process in the form of voice transcription equipment and teaching large screen projection or software on the teaching large screen terminal. Although the teaching voice subtitles can be displayed in real time, they can only be viewed within the classroom of the smart classroom and through the large screen. If you want to achieve multi-terminal access, especially remote teaching access, there are still great shortcomings.

[0096] Above Figure 1The method of multi-display terminal linkage adopted in the embodiment can simultaneously display the voice transcription subtitles of smart teaching on the smart teaching large screen, smart teaching pad and smart teaching mobile phone APP in real time. Through the docking of a separate voice transcription system and the unified management platform of the smart classroom and the docking of multiple teaching terminals, each display terminal is triggered to generate and display subtitle data through audio transcription and real-time transcription and subtitle display, which can realize multi-terminal real-time display of smart teaching subtitles, both locally and remotely. This method can solve the problem that students are inconvenient to watch the teaching large screen during smart teaching, or need to take classes remotely, and can view the voice real-time subtitles in the smart teaching process in real time.

[0097] The following combination Figure 2 , taking the application of the subtitle display method provided in the embodiment of this specification in the teaching scenario as an example, the subtitle display method is further described. Figure 2 A flowchart of a processing process of a subtitle display method provided by an embodiment of this specification applied to a teaching scenario is shown. The method is applied to the server of a subtitle system of a smart classroom, and the server includes an audio processor, a voice transcription server, and a unified management platform server, including the following specific steps: Step 202: Acquire voice data collected by the microphone from the teaching scene.

[0098] Step 204: pre-process the voice data on the audio processor to obtain pre-processed voice data.

[0099] Step 206: On the voice transcription server, the voice data is transcribed into voice text using automatic voice recognition technology to obtain text data.

[0100] Step 208: On the unified management platform server, the text data is encapsulated using the WebSocket protocol to obtain network packet data.

[0101] Step 210: Distribute the network packet data to the three display terminals, namely, a tablet computer, a smart teaching screen and a smart phone, through the WebSocket interfaces corresponding to the three display terminals preset on the unified management platform server, so that the three display terminals generate and display subtitle data in real time based on the text data in the network data packet.

[0102] In the embodiments of this specification, the speech transcription subtitles are transcribed through a speech transcription server. After the speech transcription server transcribes the subtitles, it is synchronously transmitted to the smart teaching unified management platform server for real-time processing of interface data. The three display terminals, tablet computers, smart teaching large screens, and smart phones, trigger the generation of display subtitle data by obtaining network packet data distributed by the unified management platform, thereby realizing the real-time display of speech transcription subtitles. Instant communication is achieved through the WebSocket protocol, and data is updated in real time. The speech transcription data is processed and transmitted by each node device on the server to generate subtitle data in real time, which can be displayed locally, remotely, and on multiple terminals.

[0103] See also Figure 3 , Figure 3 A flowchart of another subtitle display method provided according to an embodiment of the present specification is shown. The method is applied to a first display terminal of a subtitle system, where the first display terminal is any one of at least one display terminal in the subtitle system, and the subtitle system further includes a server. The method includes the following specific steps: Step 302: receiving network packet data sent by the server through a data transmission interface corresponding to at least one display terminal, wherein the network packet data is obtained by encapsulating text data, the text data is obtained by transcribing voice data into text, and the voice data is collected from the target scene; The first display terminal is any network terminal in the subtitle system that is used to receive network packet data, generate and display subtitle data of the target scene based on text data, including but not limited to at least one of the following: a smart phone, a tablet computer, a personal computer, a smart TV, a smart screen, etc.

[0104] In an optional embodiment of the present specification, the target scene includes a teaching scene.

[0105] Exemplarily, a network data packet sent by a server of a subtitle system through a data transmission interface corresponding to at least one display terminal is received: 0x81 0x36 0xe4 0xbd 0xa0 0xe4 0xbd 0xa0 0xe8 0xa6 0x81 0xe5 0xad 0xab0xe7 0x9a 0x84 0xe6 0x98 0xaf 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe50x87 0xa0 0xe7 0x9a 0x84 0xe5 0x9b 0xbe 0xe5 0x83 0x8f 0xe5 0x92 0x8c 0xe60x80 0xa7 0xe8 0xb4 0xa8 0xe3 0x80 0x82 0xe9 0xa6 0x96 0xe5 0x85 0xa8 0xe60x88 0x91 0xe4 0xbb 0xac 0xe6 0x9d 0xa5 0xe7 0x9c 0x8b 0xe4 0xb8 0x80 0xe40xba 0b 0xe4 0xba 0x8c 0xe6 0ac 0xe6 0x95 0xb0 0xe7 0x9a 0x84 0xe5 0xae 0x9a0xe4 0xb9 0x89 0xe3 0x80 0x82.

[0106] The network packet data sent by the server is received through a data transmission interface corresponding to at least one display terminal, laying a foundation for subsequent parsing to obtain text data.

[0107] Step 304: Parse the network packet data to obtain text data.

[0108] An optional way to parse the network packet data and obtain the text data is: An optional way is: parse the header information of the network packet data, extract the control information, and extract the text data based on the control information.

[0109] For example, parse the header information of the network packet data and extract the control information: 0x81 0x36 indicates that this is a data packet of the WebSocket protocol, where 0x81 indicates that this is a text frame, and 0x36 indicates that the payload length is 54 bytes. According to the control information, extract 54 bytes of payload information as text data: Today we are going to learn about the graph and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0110] Parse network packet data to obtain text data, providing data content support for subsequent generation and display of subtitle data.

[0111] Step 306: Generate and display subtitle data of the target scene based on the text data.

[0112] Based on the text data, subtitle data of the target scene is generated and displayed. An optional manner is: based on the text data, subtitle data of the target scene is generated and displayed according to a preset style and display position of the display terminal.

[0113] For example, for tablets and smartphones, use HTML / CSS: Create a subtitle layer: Create a subtitle layer in HTML. element.

[0114] Set style: Use CSS to set the style of the subtitles, such as font size, color, background color, transparency, etc.

[0115] Display subtitles: Insert the parsed text data into the subtitle layer and set the display position.

[0116] Generate and display the subtitle data of the target scene according to the preset style and display position of the display terminal: Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0117] For example, for a smart screen, a native API is used to generate a subtitle layer, and the style and display position are set. According to the preset style and display position of the display terminal, the subtitle data of the target scene is generated and displayed: Today we are going to learn about the image and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0118] Figure 4 FIG. 1 shows a schematic diagram of another subtitle display method provided by an embodiment of the present specification applied to a teaching scenario. Figure 4 As shown: On the application interface of the smartphone, there is a teaching scene, including multimedia images of the teacher and the blackboard. Among them, the blackboard is written with the teaching blackboard: "Graphic Definition and Properties of Quadratic Functions ----------------------- 1. Definition: -General form: y = ax^2 + bx + c (a ≠ 0) -Standard form: y = a (xh) ^ 2 + k 2. Image: -parabola -Opening direction: a>0 upward, a<0 ​​downward -Vertex coordinates: (h, k) or (-b / 2a, f(-b / 2a)) 3. Nature: -Symmetry axis: x=-b / 2a -Zero point: Solve the equation ax^2+bx+c=0 -Discriminant Δ=b^2-4ac -Δ>0: two different real roots -Δ=0: a real root (repeated root) -Δ<0: no real roots 4. Application: - Physics: Projectile Motion" The teacher teaches according to the teaching blackboard, and the microphone collects the teacher's teaching voice.

[0119] go through Figure 1 The server-side processing of the subtitle system of the embodiment receives the distributed network data packet on the smart phone, parses the network packet data, obtains text data, and generates and displays subtitle data of the target scene based on the text data: Live subtitles: Today we are going to learn about the graphs and properties of quadratic functions. First, let's look at the definition of quadratic functions.

[0120] In the embodiments of this specification, by concentrating the computational tasks of voice-to-text conversion on the server side, the display terminal only needs to parse the network packet data, obtain the text data, and generate and display the subtitle data of the target scene based on the text data, which reduces the computational burden of the display terminal, significantly reduces the delay of subtitle generation and display, improves the user experience, avoids the complexity and cost of each display terminal completing voice transcription independently, and improves the overall performance and scalability of the subtitle system. In addition, at least one data transmission interface corresponding to the display terminal is preset on the server side to ensure that the server side can efficiently and reliably distribute the network packet data to each display terminal, thereby improving the reliability and stability of the subtitle display.

[0121] The above is an illustrative solution of another subtitle display method of this embodiment. It should be noted that the technical solution of the subtitle display method is the same as the above Figure 1 The technical solution of the subtitle display method belongs to the same concept. For details not described in detail in the technical solution of the subtitle display method, please refer to the above Figure 1 Description of the technical solution of the subtitle display method.

[0122] Corresponding to the above method embodiment, this specification also provides a subtitle system embodiment. Figure 5 FIG. 2 shows a schematic diagram of a subtitle system provided by an embodiment of the present specification. Figure 5 As shown, the subtitle system 500 includes a server 510 and at least one display terminal 520, the server includes an audio processor 5110, a voice transcription server 5120, and a unified management platform server 5130, and the data transmission interface corresponding to the at least one display terminal 520 is a full-duplex transmission interface corresponding to the at least one display terminal 520 preset on the unified management platform server 5130; The audio processor 5110 is used to pre-process the voice data collected by the acquisition device from the target scene to obtain pre-processed voice data, wherein the pre-processing includes but is not limited to: at least one of noise reduction, volume standardization, removal of silence segments, echo cancellation, and format conversion; The speech transcription server 5120 is used to transcribe the speech data into text to obtain text data; The unified management platform server 5130 is used to encapsulate the text data using a full-duplex transmission protocol to obtain network packet data, and distribute the network packet data to at least one display terminal 520 through a full-duplex transmission interface corresponding to at least one display terminal 520; At least one display terminal 520 is used to receive the network packet data sent by the server 510, parse the network packet data, obtain text data, and generate and display subtitle data of the target scene based on the text data.

[0123] Corresponding to the above method embodiment, taking the target scene as a teaching scene as an example, Figure 6 A schematic diagram of a subtitle system provided by an embodiment of the present specification is shown. Figure 6 As shown: The microphone collects voice data from the teaching scene and transmits it to the audio processor 5110; The audio processor 5110 pre-processes the voice data, obtains the pre-processed voice data, and transmits it to the voice transcription server 5120; The voice transcription server 5120 transcribes the voice data into text, obtains text data, and transmits it to the unified management platform server 5130 through the transmission interface; The unified management platform server 5130 uses the full-duplex transmission protocol to encapsulate the text data, obtain network packet data, and distribute the network packet data to each display terminal through the full-duplex transmission interface corresponding to each display terminal; Real-time subtitle display on tablet computers; Real-time subtitle display on the smart teaching big screen; Real-time subtitle display on smartphone app.

[0124] The above is a schematic scheme of a subtitle system of this embodiment. It should be noted that the technical scheme of the subtitle system and the technical scheme of the above subtitle display method belong to the same concept, and the details of the technical scheme of the subtitle system that are not described in detail can all be referred to the description of the technical scheme of the above subtitle display method.

[0125] Figure 7 The block diagram of a computing device 700 according to an embodiment of the present specification is shown. The components of the computing device 700 include but are not limited to a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and the database 750 is used to store data.

[0126] The computing device 700 also includes an access device 740 that enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 740 may include one or more of any type of network interface (e.g., a Network Interface Controller (NIC)) of wired or wireless type, such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, and a Near Field Communication (NFC).

[0127] In one embodiment of the present specification, the above components of the computing device 700 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0128] The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 700 may also be a mobile or stationary server or server cluster system.

[0129] The processor 720 is used to execute the following computer program / instruction, which implements the steps of the above-mentioned subtitle display method when executed by the processor.

[0130] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above subtitle display method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above subtitle display method.

[0131] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned subtitle display method when executed by a processor.

[0132] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned subtitle display method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned subtitle display method.

[0133] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned subtitle display method when executed by a processor.

[0134] The above is a schematic solution of a computer program product of this embodiment. It should be noted that the technical solution of the computer program product and the technical solution of the above-mentioned subtitle display method belong to the same concept, and the details not described in detail in the technical solution of the computer program product can be referred to the description of the technical solution of the above-mentioned subtitle display method.

[0135] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0136] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the contents contained in the computer readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0137] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0138] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A subtitle display method, characterized in that: The method is applied to a server of a subtitle system, wherein the subtitle system further comprises at least one display terminal; and the method comprises: Acquire speech data collected from a target scene; Performing voice-to-text transcription on the voice data to obtain text data; Encapsulating the text data to obtain network packet data; The network packet data is distributed to the at least one display terminal through a data transmission interface corresponding to the at least one display terminal, so that each display terminal generates and displays the subtitle data of the target scene based on the text data in the network packet data.

2. The method according to claim 1, characterized in that: Before the voice data is transcribed into text to obtain text data, the method further includes: The voice data is preprocessed to obtain the preprocessed voice data, wherein the preprocessing includes but is not limited to: at least one of noise reduction, volume normalization, removal of silence segments, echo cancellation, and format conversion.

3. The method according to claim 1 or 2, characterized in that: The step of performing voice-to-text transcription on the voice data to obtain text data includes: The voice data is transcribed into text using automatic speech recognition technology to obtain text data.

4. The method according to claim 1, characterized in that: The step of encapsulating the text data to obtain network packet data includes: The text data is encapsulated using a full-duplex transmission protocol to obtain network packet data.

5. The method according to claim 1, characterized in that The service end includes a unified management platform server, and the data transmission interface corresponding to the at least one display terminal is a full-duplex transmission interface corresponding to the at least one display terminal preset on the unified management platform server.

6. The method according to claim 1, characterized in that The target scene includes a teaching scene.

7. A subtitle display method, characterized in that: A first display terminal applied to a subtitle system, wherein the first display terminal is any one of at least one display terminal in the subtitle system, and the subtitle system further includes a server; the method includes: Receiving network packet data sent by the server through a data transmission interface corresponding to the at least one display terminal, wherein the network packet data is obtained by encapsulating text data, the text data is obtained by transcribing voice data into text, and the voice data is collected from a target scene; Parsing the network packet data to obtain the text data; Based on the text data, subtitle data of the target scene is generated and displayed.

8. The method according to claim 7, characterized in that The target scene includes a teaching scene.

9. A subtitle system, characterized in that: It includes a server and at least one display terminal, the server includes an audio processor, a voice transcription server, and a unified management platform server, and the data transmission interface corresponding to the at least one display terminal is a full-duplex transmission interface corresponding to the at least one display terminal preset on the unified management platform server; The audio processor is used to pre-process the voice data collected by the acquisition device from the target scene to obtain the pre-processed voice data, wherein the pre-processing includes but is not limited to: at least one of noise reduction, volume standardization, removal of silence segments, echo cancellation, and format conversion; The voice transcription server is used to transcribe the voice data into text to obtain text data; The unified management platform server is used to encapsulate the text data using a full-duplex transmission protocol to obtain network packet data, and distribute the network packet data to the at least one display terminal through a full-duplex transmission interface corresponding to the at least one display terminal; The at least one display terminal is used to receive the network packet data sent by the server, parse the network packet data, obtain the text data, and generate and display the subtitle data of the target scene based on the text data.

10. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: It stores a computer program / instruction, which implements the steps of the method described in any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The method comprises a computer program / instruction which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Images