Multi-microphone conference data management system and method based on voice recognition

Through voice recognition technology, intelligent management of personnel and content is achieved in the multi-microphone conference system, the complexity of personnel management and content sorting on large-scale conference sites is solved, accurate identification and real-time marking of spokesperson identities are realized, and conference management is improved efficiency.

CN119071424AInactive Publication Date: 2024-12-03JIANGMEN JINFENG BEIKA AUDIO & VIDEO TECH CO LTD

Patent Information

Application Number
CN202411355832.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-27
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing conference systems have complexity and inefficiency in personnel management and content collation in multi-microphone meetings, especially in the difficulty in accurately identifying spokespersons and manager check-in processes at large meeting sites.

Method used

Adopt a multi-microphone conference data management system based on voice recognition, and through voice interaction technology, voiceprint recognition technology and voice-text conversion technology, intelligent management of personnel and conference content, including microphone setting module, conference audio data module, check-in module, The video real-time positioning module and the video identity information marking module support different microphone binding types and check-in methods, and real-time identification and marking of spokesperson identities.

Benefits of technology

It realizes convenient management of the identity of personnel in the meeting and rapid organization of content, can accurately identify the identity of the spokesperson under different microphone types and check-in methods, and mark it in real-time video, improving the efficiency and accuracy of meeting management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071424A_ABST
    Figure CN119071424A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-microphone conference data management system and method based on voice recognition, and belongs to the field of audio and video conferences, and the system comprises a microphone setting module which is used for configuring the microphone information of a conference and setting the binding type of each microphone; the conference audio data module is used for acquiring audio data of each microphone in a main conference place and audio data of a remote conference terminal; the conference personnel sign-in module is used for determining a sign-in mode, generating a sign-in instruction and realizing sign-in by performing voice recognition and voiceprint recognition on the acquired audio data; the video real-time positioning module is used for adjusting camera positioning according to microphone information corresponding to the real-time audio data; and the video identity information marking module is used for determining bound personnel identity information according to the microphone information corresponding to the real-time audio data, and marking the personnel identity information in the video data partial region. According to the invention, the audio and video conference sign-in and data management efficiency can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of audio and video conferencing, and in particular to a multi-microphone conference data management system and method based on speech recognition. Background Art

[0002] The current conference system, whether in terms of the overall system or the equipment, is still only at the stage of solving the information transmission and conference process problems in the conference. Personnel management for multi-microphone conferences is still handled manually. Especially in some large conferences, the specific personnel arrangement and management is very complicated, with fixed seats and random seats, fixed microphones and wireless microphones, etc., which easily leads to omissions or errors in the sign-in process and personnel position arrangement process.

[0003] Not only that, at large conferences, people in randomly assigned seats make speeches, and it is difficult for those at the conference to determine the specific identities of the speakers. When the content of the meeting needs to be sorted out after the meeting, it also takes a huge amount of effort to sort out the identities of the people and the content of their speeches.

[0004] Therefore, there is an urgent need for a multi-microphone conference management system that can combine the characteristics of multi-microphone conferences to conveniently manage personnel identities and quickly organize conference content. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a multi-microphone conference data management system and method based on voice recognition, which can realize intelligent management of personnel and conference content through voice interaction technology, voiceprint recognition technology and voice-to-text conversion technology.

[0006] On the one hand, an embodiment of the present invention provides a multi-microphone conference data management system based on voice recognition, including: a microphone setting module, used to configure the microphone information of the conference and set the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the participants bound to it; a conference audio data module, used to obtain the audio data of each microphone in the main venue and the audio data of the remote conference terminal; a conference personnel sign-in module, used to determine the sign-in method according to the conference microphone type information and the received sign-in application information, and generate a sign-in instruction, perform voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the sign-in instruction When the person's identity information matches the person's identity information in the application information, the sign-in is successful; the sign-in methods include remote sign-in, random sign-in, microphone-bound sign-in and fixed microphone sign-in; when the sign-in method is microphone-bound sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of on-site binding; when the sign-in method is fixed microphone sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of preset binding; a video real-time positioning module is used to adjust the camera positioning according to the microphone information corresponding to the real-time audio data to obtain the video data of the current speaker; a video identity information marking module is used to determine the bound person's identity information according to the microphone information corresponding to the real-time audio data, and mark the person's identity information in a partial area of ​​the video data.

[0007] The embodiments of the invention achieve at least the following beneficial effects: The embodiments of the invention achieve intelligent management of personnel and conference content through voice interaction technology, voiceprint recognition technology and voice-to-text conversion technology. The embodiments of the invention set different binding types according to different microphone characteristics and conference usage requirements, which are suitable for different situations and can realize the binding of personnel and microphones. The identity information of the speaker can be determined without voiceprint recognition in the conference; the embodiments of the invention set different sign-in methods according to the conference microphone type and the identity of specific personnel. Conference personnel can sign in according to the voiceprint recognition method and bind their identities with the microphone at the same time; because the microphone is bound to part of the personnel identity information, the identity of the speaker can be determined in time during the meeting and the identity can be marked in the real-time video of the venue, so that the personnel in the meeting can determine the identity of the speaker.

[0008] According to some embodiments of the present invention, the conference personnel sign-in module includes: a sign-in method unit, used to obtain the conference microphone type information and the personnel identity information in the sign-in application information. If the microphone binding type includes unbound and the personnel identity information does not exist in the microphone preset binding list, the optional sign-in method includes random sign-in; if the microphone binding type includes on-site binding and the personnel identity information does not exist in the microphone preset binding list, the optional sign-in method includes bound microphone sign-in; if the personnel identity information exists in the microphone preset binding list, the optional sign-in method only includes fixed microphone sign-in; if the personnel identity information is in the remote conference personnel list, the sign-in method includes remote sign-in; the optional sign-in method is fed back to the sign-in application terminal.

[0009] According to some embodiments of the present invention, the conference personnel sign-in module includes: a random sign-in unit, which is used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in method is random sign-in, and then obtain audio data through each microphone for voice recognition and voiceprint recognition. When the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the personnel identity information in the sign-in application information, the sign-in is successful; a bound microphone sign-in unit, which is used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in method is bound microphone sign-in, and then obtain audio data through each microphone with the binding type of on-site binding for Speech recognition and voiceprint recognition, when the speech recognition obtains the sign-in instruction and the voiceprint recognition result matches the personal identity information in the sign-in application information, the sign-in is successful and the personal identity information is bound to the microphone that currently recognizes the sign-in instruction; a fixed microphone sign-in unit, used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in method is fixed-position sign-in, and then obtain the audio data of the microphone pre-bound to the personal identity information for speech recognition and voiceprint recognition. When the speech recognition obtains the sign-in instruction and the voiceprint recognition result matches the personal identity information in the sign-in application information, the sign-in is successful.

[0010] According to some embodiments of the present invention, the conference personnel check-in module includes: a remote check-in unit, which is used to obtain audio data from the remote conference terminal for voice recognition and voiceprint recognition. When the voice recognition obtains the check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful.

[0011] According to some embodiments of the present invention, the real-time video positioning module includes: a microphone positioning unit, which is used to set the microphone positioning data of a movable camera according to the specific position of a microphone set at a fixed position; a camera adjustment unit, which is used to position the camera to the position of the microphone when the microphone corresponding to the current audio data is a microphone set at a fixed position; when the microphone corresponding to the current audio data is a mobile microphone, the camera is positioned to a position where the panoramic view of the venue can be seen.

[0012] According to some embodiments of the present invention, the video identity information marking module includes: a microphone type identification unit, which is used to obtain the binding type of the microphone of the current speaker. If the binding type is on-site binding or preset binding, the identity information of the person bound to the current microphone is obtained and marked in the main venue video reserved area; a voiceprint recognition unit, which is used to obtain the audio data of the current speaker for voiceprint recognition when the binding type is unbound, obtain the person's identity information and mark it in the main venue video reserved area.

[0013] According to some embodiments of the present invention, the system further includes: a conference data sorting module, which is used to perform speech recognition on audio data in the conference to obtain conference speech text, and match the conference speech text with the identity information of the speaker to obtain conference data.

[0014] According to some embodiments of the present invention, the system also includes: a conference incentive module, which is used to obtain the text of the conference host's speech from the conference data and perform keyword positioning based on the preset conference host identity information, and obtain the identity information of the previous speaker at the keyword location to generate an incentive list.

[0015] According to some embodiments of the present invention, the system further comprises: a personnel identity information database module, configured to store personnel identity information and corresponding voiceprint identity information.

[0016] On the other hand, an embodiment of the present invention provides a multi-microphone conference data management method based on voice recognition, including: S100, configuring the microphone information of the conference and setting the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the participants bound to it; S200, obtaining the audio data of each microphone in the main venue and the audio data of the remote conference terminal; S300, determining the sign-in method according to the conference microphone type information and the received sign-in application information, and generating a sign-in instruction, performing voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the sign-in instruction and the voiceprint recognition result is consistent with the sign-in instruction, the sign-in instruction is generated. When the person identity information in the application information matches, the sign-in is successful; the sign-in methods include remote sign-in, random sign-in, microphone-bound sign-in and fixed microphone sign-in; when the sign-in method is microphone-bound sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of on-site binding; when the sign-in method is fixed microphone sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of preset binding; S400, adjust the camera positioning according to the microphone information corresponding to the real-time audio data, and obtain the video data of the current speaker; S500, determine the bound person identity information according to the microphone information corresponding to the real-time audio data, and mark the person identity information in a partial area of ​​the video data.

[0017] The embodiments of the present invention achieve at least the following beneficial effects: The embodiments of the present invention realize intelligent management of personnel and conference content through voice interaction technology, voiceprint recognition technology and voice-to-text conversion technology. The embodiments of the present invention set different binding types according to different microphone characteristics and conference usage requirements, which are applicable to different situations, and can realize the binding of personnel and microphones, and the identity information of the speaker can be determined without voiceprint recognition in the conference; the embodiments of the present invention set different sign-in methods according to the conference microphone type and the identity of specific personnel, and the conference personnel can sign in according to the voiceprint recognition method and bind their identities with the microphone; because the microphone is bound to part of the personnel identity information, the identity of the speaker can be determined in time during the meeting and the identity can be marked in the real-time video of the venue, so that the personnel in the meeting can determine the identity of the speaker.

[0018] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0020] Figure 1 Schematic diagram of the structure of the system according to the embodiment of the present invention.

[0021] Figure 2 The figure is a flowchart of a method according to an embodiment of the present invention.

[0022] Reference numerals:

[0023] Microphone setting module 100, conference audio data module 200, conference personnel check-in module 300, video real-time positioning module 400, video identity information marking module 500. DETAILED DESCRIPTION

[0024] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0025] In the description of the present invention, "several" means one or more, "more" means two or more, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0026] Speech recognition technology: Speech recognition technology is a high-tech technology that allows machines to convert speech signals into corresponding text or commands through the process of recognition and understanding. Speech recognition technology mainly includes three aspects: feature extraction technology, pattern matching criteria and model training technology.

[0027] Voiceprint recognition technology: Voiceprint is a sound wave spectrum that carries speech information and is displayed by electroacoustic instruments. The production of human language is a complex physiological and physical process between the human body's language center and the vocal organs. The vocal organs used by people when speaking - tongue, teeth, larynx, lungs, and nasal cavity - vary greatly in size and shape from person to person, so the voiceprints of any two people are different. Voiceprint recognition, a type of biometric technology, is also called speaker recognition, which includes speaker identification and speaker confirmation. Voiceprint recognition is to convert sound signals into electrical signals and then use computers to identify them.

[0028] The embodiments of the present invention are applicable to multi-microphone conferences in various situations. For example, if the number of microphones meets the number of participants and the positions are not fixed, the microphones can be bound to the participants one by one, thereby facilitating the organization of the conference content. For another example, if the number of microphones is insufficient, some important participants need fixed microphones, and some wireless microphones are used to meet the needs of other participants. In this case, different sign-in methods can be used to meet the needs of personnel management and determine the microphones used by some important participants, thereby facilitating the organization of the conference content. There are other situations that are not listed here.

[0029] Reference Figure 1 The embodiment of the present invention proposes a multi-microphone conference data management system based on speech recognition, comprising:

[0030] The microphone setting module 100 is used to configure the microphone information of the conference and set the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the participants bound to it.

[0031] The conference audio data module 200 is used to obtain audio data from microphones in the main conference room and audio data from remote conference terminals.

[0032] The conference personnel check-in module 300 is used to determine the check-in method according to the conference microphone type information and the received check-in application information, generate a check-in instruction, perform voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful; the check-in methods include remote check-in, random check-in, bound microphone check-in and fixed microphone check-in; when the check-in method is bound microphone check-in, after the check-in is successful, the identity information of the check-in person is bound to the microphone with the binding type of on-site binding; when the check-in method is fixed microphone check-in, after the check-in is successful, the identity information of the check-in person is bound to the microphone with the binding type of preset binding.

[0033] The video real-time positioning module 400 is used to adjust the camera positioning according to the microphone information corresponding to the real-time audio data to obtain the video data of the current speaker.

[0034] The video identity information marking module 500 is used to determine the bound person identity information according to the microphone information corresponding to the real-time audio data, and mark the person identity information in a partial area of ​​the video data.

[0035] In some embodiments, the conference personnel check-in module 300 includes: a check-in method unit, used to obtain the conference microphone type information and the personnel identity information in the check-in application information. If the microphone binding type includes unbound and the personnel identity information does not exist in the microphone preset binding list, the optional check-in method includes random check-in; if the microphone binding type includes on-site binding and the personnel identity information does not exist in the microphone preset binding list, the optional check-in method includes bound microphone check-in; if the personnel identity information exists in the microphone preset binding list, the optional check-in method only includes fixed microphone check-in; if the personnel identity information is in the remote conference personnel list, the check-in method includes remote check-in; the optional check-in method is fed back to the check-in application terminal.

[0036] In some embodiments, the conference personnel check-in module 300 includes: a random check-in unit, which is used to generate and send a check-in instruction to the check-in application terminal when the check-in method is random check-in, and then obtain audio data through each microphone for voice recognition and voiceprint recognition. When the voice recognition obtains the check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful.

[0037] In some embodiments, the conference personnel check-in module 300 includes: a microphone binding check-in unit, which is used to generate and send a check-in instruction to the check-in application terminal when the check-in method is microphone binding check-in, and then obtain audio data through each microphone with a binding type of on-site binding for voice recognition and voiceprint recognition. When the voice recognition obtains the check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful and the personnel identity information is bound to the microphone that currently recognizes the check-in instruction.

[0038] In some embodiments, the conference personnel check-in module 300 includes: a fixed microphone check-in unit, which is used to generate and send a check-in instruction to the check-in application terminal when the check-in method is fixed location check-in, and then obtain the audio data of the microphone pre-bound to the personnel identity information for voice recognition and voiceprint recognition. When the voice recognition obtains the check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful.

[0039] In some embodiments, the conference personnel check-in module 300 includes: a remote check-in unit, which is used to obtain audio data from the remote conference terminal for voice recognition and voiceprint recognition. When the voice recognition obtains a check-in instruction and the voiceprint recognition result matches the personnel identity information in the check-in application information, the check-in is successful.

[0040] In some embodiments, the real-time video positioning module 400 includes: a microphone positioning unit, which is used to set the microphone positioning data of the movable camera according to the specific position of the microphone set at a fixed position; a camera adjustment unit, which is used to position the camera to the position of the microphone when the microphone corresponding to the current audio data is a microphone set at a fixed position; when the microphone corresponding to the current audio data is a mobile microphone, the camera is positioned to a position where the panoramic view of the venue can be seen.

[0041] In some embodiments, the video identity information marking module 500 includes: a microphone type identification unit, which is used to obtain the binding type of the current speaker's microphone. If the binding type is on-site binding or preset binding, the identity information of the person bound to the current microphone is obtained and marked in the main venue video reserved area; a voiceprint recognition unit, which is used to obtain the audio data of the current speaker for voiceprint recognition when the binding type is unbound, obtain the person's identity information and mark it in the main venue video reserved area.

[0042] In some embodiments, the system of the embodiment of the present invention also includes: a conference data sorting module, which is used to perform speech recognition on the audio data in the meeting to obtain conference speech text, and match the conference speech text with the identity information of the speaker to obtain conference data.

[0043] In some embodiments, the system of the embodiment of the present invention also includes: a conference incentive module, which is used to obtain the text of the conference host's speech from the conference data and perform keyword positioning based on the preset conference host identity information, and obtain the identity information of the previous speaker at the keyword location to generate an incentive list.

[0044] In some embodiments, the system of the embodiment of the present invention further includes: a personnel identity information database module, which is used to store personnel identity information and corresponding voiceprint identity information.

[0045] Reference Figure 2 The embodiment of the present invention provides a multi-microphone conference data management method based on speech recognition, comprising:

[0046] S100, configuring the microphone information of the conference and setting the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the participant bound thereto.

[0047] S200: Acquire audio data from microphones at the main conference site and audio data from remote conference terminals.

[0048] S300. Determine the sign-in method according to the conference microphone type information and the received sign-in application information, generate a sign-in instruction, perform voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the personnel identity information in the sign-in application information, the sign-in is successful; the sign-in methods include remote sign-in, random sign-in, bound microphone sign-in and fixed microphone sign-in; when the sign-in method is bound microphone sign-in, after the sign-in is successful, the identity information of the sign-in person is bound to the microphone with the binding type of on-site binding; when the sign-in method is fixed microphone sign-in, after the sign-in is successful, the identity information of the sign-in person is bound to the microphone with the binding type of preset binding.

[0049] S400: Adjust the camera positioning according to the microphone information corresponding to the real-time audio data to obtain the video data of the current speaker.

[0050] S500: Determine the bound person identity information according to the microphone information corresponding to the real-time audio data, and mark the person identity information in a partial area of ​​the video data.

[0051] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0052] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to the exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.

[0053] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.

[0054] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.

[0055] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages ​​include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages ​​or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.

[0056] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0057] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A multi-microphone conference data management system based on speech recognition, characterized in that: include: A microphone setting module is used to configure the microphone information of the conference and set the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the participants bound to it; Conference audio data module, used to obtain audio data from microphones in the main conference room and audio data from remote conference terminals; The conference personnel sign-in module is used to determine the sign-in method according to the conference microphone type information and the received sign-in application information, generate a sign-in instruction, perform voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the personnel identity information in the sign-in application information, the sign-in is successful; the sign-in methods include remote sign-in, random sign-in, microphone-bound sign-in and fixed microphone sign-in; when the sign-in method is microphone-bound sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of on-site binding; when the sign-in method is fixed microphone sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone with a binding type of preset binding; The video real-time positioning module is used to adjust the camera positioning according to the microphone information corresponding to the real-time audio data to obtain the video data of the current speaker; The video identity information marking module is used to determine the bound person identity information according to the microphone information corresponding to the real-time audio data, and mark the person identity information in a part of the video data area.

2. The multi-microphone conference data management system based on speech recognition according to claim 1 is characterized in that: The conference staff sign-in module includes: The sign-in method unit is used to obtain the conference microphone type information and the personnel identity information in the sign-in application information. If the microphone binding type includes unbound and the personnel identity information does not exist in the microphone preset binding list, the optional sign-in method includes random sign-in; if the microphone binding type includes on-site binding and the personnel identity information does not exist in the microphone preset binding list, the optional sign-in method includes bound microphone sign-in; if the personnel identity information exists in the microphone preset binding list, the optional sign-in method only includes fixed microphone sign-in; if the personnel identity information is in the remote conference personnel list, the sign-in method includes remote sign-in; the optional sign-in method is fed back to the sign-in application terminal.

3. The multi-microphone conference data management system based on speech recognition according to claim 1 is characterized in that: The conference staff sign-in module includes: The random sign-in unit is used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in mode is random sign-in, and then obtain audio data through each microphone for voice recognition and voiceprint recognition. When the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the person identity information in the sign-in application information, the sign-in is successful; A microphone binding sign-in unit is used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in mode is microphone binding sign-in, and then obtain audio data through microphones of each binding type as on-site binding for voice recognition and voiceprint recognition. When the sign-in instruction is obtained by voice recognition and the voiceprint recognition result matches the person identity information in the sign-in application information, the sign-in is successful and the person identity information is bound to the microphone that currently recognizes the sign-in instruction; The fixed microphone sign-in unit is used to generate and send a sign-in instruction to the sign-in application terminal when the sign-in method is fixed-location sign-in, and then obtain the audio data of the microphone pre-bound to the personnel identity information for voice recognition and voiceprint recognition. When the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the personnel identity information in the sign-in application information, the sign-in is successful.

4. The multi-microphone conference data management system based on speech recognition according to claim 1, characterized in that: The conference staff sign-in module includes: The remote sign-in unit is used to obtain the audio data of the remote conference terminal for voice recognition and voiceprint recognition. When the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the person identity information in the sign-in application information, the sign-in is successful.

5. The multi-microphone conference data management system based on speech recognition according to claim 1, characterized in that: The video real-time positioning module includes: A microphone positioning unit, used to set microphone positioning data of a movable camera according to a specific position of a microphone arranged at a fixed position; The camera adjustment unit is used to position the camera to the position of the microphone when the microphone corresponding to the current audio data is set at a fixed position; when the microphone corresponding to the current audio data is a mobile microphone, the camera is positioned to a position where the panoramic view of the venue can be seen.

6. The multi-microphone conference data management system based on speech recognition according to claim 1, characterized in that: The video identity information marking module includes: A microphone type identification unit is used to obtain the binding type of the microphone of the current speaker. If the binding type is on-site binding or preset binding, the identity information of the person bound to the current microphone is obtained and marked in the main venue video reserved area; The voiceprint recognition unit is used to obtain the audio data of the current speaker for voiceprint recognition when the binding type is unbound, obtain the person's identity information and mark it in the reserved area of ​​the main venue video.

7. The multi-microphone conference data management system based on speech recognition according to claim 1, characterized in that: The system further comprises: The conference data sorting module is used to perform speech recognition on the audio data in the conference to obtain the conference speech text, and match the conference speech text with the identity information of the speaker to obtain the conference data.

8. The multi-microphone conference data management system based on speech recognition according to claim 7, characterized in that: The system further comprises: The conference incentive module is used to obtain the conference host's speech text from the conference data and locate keywords based on the preset conference host identity information, and obtain the identity information of the previous speaker at the keyword location to generate an incentive list.

9. The multi-microphone conference data management system based on speech recognition according to claim 1, characterized in that: The system further comprises: The personnel identity information database module is used to store personnel identity information and corresponding voiceprint identity information.

10. A multi-microphone conference data management method based on speech recognition, characterized in that: include: S100, configuring microphone information for the conference and setting the binding type of each microphone; the binding types include unbound, preset binding and on-site binding; wherein the microphone with the binding type of preset binding presets the identity information of the conference participants bound thereto; S200, obtaining audio data from each microphone in the main conference room and audio data from the remote conference terminal; S300, determining a sign-in method according to the conference microphone type information and the received sign-in application information, generating a sign-in instruction, performing voice recognition and voiceprint recognition on the acquired audio data, and when the voice recognition obtains the sign-in instruction and the voiceprint recognition result matches the person identity information in the sign-in application information, the sign-in is successful; the sign-in methods include remote sign-in, random sign-in, microphone-bound sign-in and fixed microphone sign-in; when the sign-in method is microphone-bound sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone whose binding type is on-site binding; when the sign-in method is fixed microphone sign-in, after the sign-in is successful, the sign-in person's identity information is bound to the microphone whose binding type is preset binding; S400, adjusting the camera position according to the microphone information corresponding to the real-time audio data to obtain the video data of the current speaker; S500: Determine the bound person identity information according to the microphone information corresponding to the real-time audio data, and mark the person identity information in a partial area of ​​the video data.

Citation Information

Patent Citations

  • A video conference sign-in method based on biological characteristic similarity and related equipment

    CN109670394A

  • Remote conference system and multi-microphone voice recognition playing method

    CN114257778A

  • Multifunctional conference management system, method, equipment and medium

    CN118134409A

  • Mainboard capable of automatically locking face of spokesman

    CN218071620U

Cited By

  • Voiceprint recognition method based on smart home scene and related equipment

    CN120431935A