Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for processing conference voice data

A technology of speech data and processing methods, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of wasting human resources and time costs, inconvenient search and retrieval, and confusion of speakers.

Active Publication Date: 2022-07-26
深圳极联信息技术股份有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, when a meeting is held, the process of the meeting will be recorded. At present, there are recorders on the sidelines to record, or use camera equipment to record, but it is not convenient enough. At present, there is a form of recording the meeting voice through the recording equipment, but due to There are many speakers. When recording the voice, it is easy to confuse the speaker. When sorting out the data in the later stage, it is easy to waste a lot of human resources and time costs, and it is not convenient to search and retrieve later.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for processing conference voice data
  • Method and system for processing conference voice data
  • Method and system for processing conference voice data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A method for processing conference voice data, comprising the following steps:

[0036] S110: A plurality of collection modules 201 are arranged near different conference participants, and according to different above-mentioned collection modules 201, the identity information and initial voiceprint features of the corresponding conference participants are collected to collect the speech voices of the corresponding conference participants;

[0037] S120: Identifying and judging whether the voice contents of a plurality of the above-mentioned speech voices are the same, and when they are the same, analyze the sound intensities of the plurality of above-mentioned voice contents, and select the above-mentioned voice contents with the highest sound intensity;

[0038] S130: Establish a voice feature model of a plurality of participants according to the identity information and the initial voiceprint feature, and input the selected speech voice into the voice feature model to ...

Embodiment 2

[0051] see figure 2 , figure 2 A schematic diagram of a conference voice data processing system 200 provided by an embodiment of the present invention.

[0052] A conference voice data processing system 200, comprising an error correction module 202, a confirmation module 204, an identity comparison module 203 and a plurality of collection modules 201: the plurality of above-mentioned collection modules 201 are used to be arranged near different participants, and according to different above-mentioned collection modules The module 201 collects the identity information and initial voiceprint features of the corresponding participants to collect the speech voices of the corresponding participants; the above-mentioned error correction module 202 is used to identify and judge whether the voice contents of the plurality of above-mentioned speech voices are the same, and when the same , analyze the sound intensities of a plurality of the above-mentioned voice contents, and select...

Embodiment 3

[0064] see image 3 , image 3 This is a schematic structural block diagram of an electronic device provided in an embodiment of the present application. The electronic device includes a memory 101, a processor 102, and a communication interface 103. The memory 101, the processor 102, and the communication interface 103 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, such as program instructions / modules corresponding to the conference voice processing system provided in the embodiments of the present application, and the processor 102 executes various functions by executing the software programs and modules stored in the memory 101. applications and data processing. The communication interface 103 can be used for signalin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method and system for processing speech data of a conference, and relates to the field of speech recognition. It includes the following steps: a plurality of acquisition modules are arranged near different participants, and the identity information and initial voiceprint features of the corresponding participants are collected according to different acquisition modules to collect the speech voices of the corresponding participants; Whether the voice content of the spoken voice is the same, if it is the same, analyze the sound intensity of multiple voice contents, and select the voice content with the highest sound intensity; establish the voice feature model of multiple participants according to the identity information and initial voiceprint features, and select The speech voice is input into the voice feature model to obtain the identity matching result; according to the acquisition module, it is judged whether the identity information matches the identity matching result, and when it does not match, the same voice content corresponding to the acquisition module is selected according to the identity matching result. It can improve the accuracy of voice collection of participants and improve the effect of meeting recording.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, and in particular, to a method and system for processing speech data of a conference. Background technique [0002] A meeting refers to an organized, led and purposeful discussion activity, which is carried out at a limited time and place and according to certain procedures. At present, when a meeting is held, the meeting process is recorded. At present, it is recorded by a recorder or recorded by a camera device, but it is not convenient enough. At present, there is a form of recording the meeting voice through a recording device, but due to There are many speakers. When recording voices, it is easy to confuse the speakers. When sorting out data in the later stage, it is easy to waste a lot of human resources and time costs, and it is inconvenient to search and retrieve in the later stage. SUMMARY OF THE INVENTION [0003] The purpose of the present invention is to provide ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L17/00G10L15/20G10L15/26G10L15/06G10L15/32
CPCG10L17/00G10L15/20G10L15/26G10L15/063G10L15/32G10L2015/0631
Inventor 王钰勋
Owner 深圳极联信息技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com