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

Voice separation method based on binaural sound source localization

A technology for sound source localization and voice separation, which is applied in voice analysis, positioning, and measurement devices. It can solve problems such as large amount of calculation, error of true value, and large microphone array size, and achieve the effect of improving accuracy.

Active Publication Date: 2015-03-25
SOUTHEAST UNIV
View PDF6 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the mixing matrix estimated by the blind source speech separation technology needs to manually select the peak point, and there is an error with the real value, and its implementation conditions are difficult to meet the binaural speech separation model
However, the speech separation algorithm of multi-microphone array has problems such as large amount of calculation and large size of microphone array.

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
  • Voice separation method based on binaural sound source localization
  • Voice separation method based on binaural sound source localization
  • Voice separation method based on binaural sound source localization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] The present invention first carries out data training, and uses the mean value of ITD (Interaural Time Difference) and IID (Interaural Intensity Difference) of each orientation as the location characteristic clue of the location of the sound source, and establishes the location mapping model; the actual sound source location When the input is a two-channel acoustic signal, the input acoustic signal is transformed in the frequency domain first, and the ITD and IID parameters of each frame are calculated, and the ITD characteristic parameters are matched with the orientation feature model established by the training module one by one. Based on the Euclidean distance measure, the Azimuth screening, output candidate azimuths, Euclidean distance calculation between the IID feature parameters of the frame corresponding to all candidate azimuths and the IID feature para...

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 voice separation method based on binaural sound source localization. Multiple sound sources are separated through data training, multiple-sound-source localization and voice separation according to sound source directions, and a separation voice of each sound source is obtained. The voice separation method can simulate the auditory sense of human ears based on the cocktail party effect of the human ears, the number of the sound sources and the directions of the sound sources can be accurately located, and an accurate mixed matrix is obtained through the information of the located sound source directions. Thus, the voice separation process is conducted, and the separation performance of the voice separation method is effectively improved.

Description

technical field [0001] The invention relates to a speech separation technology, in particular to a speech separation method based on binaural sound source localization. Background technique [0002] Speech separation is a special kind of speech enhancement method, which is only based on the observation data collected from binaural microphones (that is, the mixed speech signal) when the source speech signal and the transmission channel parameters (that is, the mixing process) are unknown. , the process of recovering or separating out independent source speech signals. [0003] At present, the mixing matrix estimated by the blind source speech separation technology needs to manually select the peak point, which has errors with the real value, and its implementation conditions are difficult to meet the binaural speech separation model. However, the speech separation algorithm of multi-microphone array has problems such as large amount of calculation and large size of microphon...

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): G10L21/0308G01S5/18
Inventor 周琳李枭雄吴镇扬郭海燕
Owner SOUTHEAST UNIV
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