Supercharge Your Innovation With Domain-Expert AI Agents!

Method for judging number of speakers

A speaker and purpose technology, applied in the field of speaker number judgment based on speaker segmentation and clustering, can solve problems such as inaccurate speaker numbers, achieve the goal of eliminating step size restrictions, improving accuracy, and improving speech recognition effects Effect

Inactive Publication Date: 2017-11-24
GUANGDONG QIMING TECHNOLOGY DEVELOPMENT CO LTD
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for judging the number of speakers, which solves the problem of inaccurate judgment of the number of speakers for a double-speaker scene or a multi-speaker scene, and improves the accuracy of judging the number of speakers

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 for judging number of speakers
  • Method for judging number of speakers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Based on the embodiments of the present invention, those skilled in the art can obtain the All other embodiments belong to the protection scope of the present invention.

[0034] see figure 1 , is the specific flow of the method for judging the number of speakers according to an embodiment of the present invention. The method comprises the steps of:

[0035] S1: Receive the voice digital signal and preprocess the digital signal.

[0036] The preprocessing is mainly to detect the endpoint of the digital signal, find the effective speech segment in the signal, and remove the non-speech segment.

[0037] S2: Extracting the features of the preprocessed speech signal.

[0038] The voice signal feature may be a PLP feature, and of course it may also be a voice feature s...

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 discloses a method for judging the number of speakers. The method comprises a step of receiving a voice digital signal and carrying out preprocessing on the digital signal, a step of extracting voice signal characteristics after preprocessing, a step of carrying out preliminary segmentation and preliminary judgment on the voice signal according to the voice signal characteristics, a step of judging whether the number of the speakers is larger than or equal to three, carrying out multi-people voice characteristic clustering if so, judging the number of the speakers, judging whether the number of the speakers is one or two if not. According to the method, a problem of inaccurate judgment of the number of speakers in a double-speaker scene or a three-or-more-speaker scene is solved, and the accuracy of judging the number of speakers is improved.

Description

technical field [0001] The invention relates to the technical fields of speech signal processing and pattern recognition, and in particular to a method for judging the number of speakers based on speaker segmentation and clustering. Background technique [0002] With the continuous development of speech processing technology, accurate judgment of the number of speakers can help analyze the scene of speech recording, optimize the effect of speaker separation, and formulate corresponding strategies to improve the effect of recognition. For example, a two-speaker scenario for a telephone recording; or a multi-speaker scenario for a conference recording. [0003] The accuracy of the number judgment results in the existing speaker number judgment methods completely depends on the accuracy of speaker segmentation and clustering, and because the speaker segmentation is affected by the step size, the step size is mostly determined based on experience, so it is inevitable to appear ...

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 Applications(China)
IPC IPC(8): G10L15/08G10L25/03G10L25/51G10L15/06
CPCG10L15/063G10L15/08G10L25/03G10L25/51G10L2015/0631
Inventor 李权杨有科余亮谢泽鑫陈杰永冯国梁邹月荣郭清霞陈元林
Owner GUANGDONG QIMING TECHNOLOGY DEVELOPMENT CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com