Sound signal separation method of double sound sources and sound pickup

A sound signal and separation method technology, applied in speech analysis, instruments, etc., can solve the problems of misjudgment of speech separation, untimely switching of sound source separation, and low positioning accuracy

Active Publication Date: 2020-07-17
西安声联科技有限公司
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a dual sound source sound signal separation method and a sound pickup to solve the problems of low positioning accuracy of sound source separation technology in the prior art, untimely switching of sound source separation, and misjudgment of speech separation.

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
  • Sound signal separation method of double sound sources and sound pickup
  • Sound signal separation method of double sound sources and sound pickup
  • Sound signal separation method of double sound sources and sound pickup

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0195] Scene example 1: Interrogation room scene.

[0196] In the interrogation room of the public security organ, police officers investigate and collect evidence of criminal behavior and interrogate criminal suspects, which is an important part of law enforcement. Traditional interrogation transcripts are usually organized by a special clerk, and the workload of record editing is heavy; in a large number of cases, the conversation is fast and the recording is slow, and the interrogation transcripts after sorting are prone to omission of some important issues; at the same time, some inquiry processes The details of the problems in the middle need to be reviewed through repeated recordings in the later stage.

example 2

[0197] Scenario Example 2: Service lobby or bank counter.

[0198] In order to improve service quality, traditional research methods usually use questionnaires, requiring people to spare time to cooperate with filling out the questionnaires. The finishing of the questionnaires in the later period will also consume a lot of manpower and time. The separation method provided by the present application can separate the voice information of the service personnel and the service personnel in real time, so as to judge the service quality of the service personnel.

[0199]The dual sound source separates the pickups in real time. Through multiple repeated long-term tests in different usage scenarios, it can effectively and accurately separate the voices of the two parties in the conversation, and the pickups maintain stable operation for a long time. Figure 10 A, b, and c in the middle are the dialogue voices of A and B in a group of test results, the voice of A after separation, and...

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 sound signal separation method of double sound sources and a sound pickup. The method comprises the followings steps: dividing the mixed sound signals into voice frames, estimating the delay inequality of the voice frames reaching different array element combinations in the microphone array, judging the propagation direction of the voice frames according to the determineddelay inequality, separating sound signals corresponding to different sound sources in real time according to the propagation direction, and outputting the sound signals. Time delay estimation is carried out through a generalized cross-correlation algorithm, time delay can be accurately estimated, the calculation amount of the algorithm is low, the algorithm can track the sound source orientationmore accurately and efficiently in a real-time system, and therefore automatic separation of sound signals of a first sound source and a second sound source is achieved.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a dual sound source sound signal separation method and a sound pickup. Background technique [0002] In recent years, with the rapid development of speech recognition technology, there is an urgent technical demand for real-time sound source separation technology in multi-channel speech recognition scenarios. For example, in some important meeting scenarios, real-time meeting records and recording quality play a decisive role. But as far as the current actual market is concerned, meeting records are either recorded and organized manually on the spot; Both of these methods are a very time-consuming and tedious manual work. Sound signals can be recorded by recording, but when a certain content needs to be played back, the entire recording needs to be played back, which takes a long time. [0003] There are also technologies for directional sound sources in the prior ar...

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): G10L21/028
CPCG10L21/028
Inventor 黄海刘佳隆弢
Owner 西安声联科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap