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

Sound source localization method based on acoustic bionic cochlea basal membrane

A sound source localization and basilar membrane technology, applied in positioning, speech analysis, measuring devices, etc., can solve the problems of large and complex calculation, large structure, comparable accuracy of microphone positioning technology, etc.

Inactive Publication Date: 2016-05-11
CHONGQING UNIV OF POSTS & TELECOMM
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After decades of development, the sound source localization system based on the microphone array has been very perfect, but its structure is too large, it needs a lot of microphones, and the amount of calculation is large and complicated.
Scholars have found in a large number of experimental results that the accuracy of the microphone-based positioning technology is still not comparable to the accuracy of the human ear.

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 source localization method based on acoustic bionic cochlea basal membrane
  • Sound source localization method based on acoustic bionic cochlea basal membrane
  • Sound source localization method based on acoustic bionic cochlea basal membrane

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further explained below in conjunction with the drawings:

[0039] Such as figure 1 As shown, in response to the problem of low positioning accuracy caused by the inability of traditional sound source positioning to obtain high signal-to-noise ratio sound source signals in a noisy environment, this paper combines the characteristics of human ears to propose a hearing selection ability based on human ears, namely " The process of selecting the source of noise in the "cocktail party effect". The noisy sound source signal is subjected to frequency spectrum analysis through the cochlear basement membrane model, the signal conversion is performed through the inner hair cell model on the cochlear basement membrane, and the nerve fibers on the inner hair cell are overlapped, and then voice information is performed through the upper olive nucleus model Extract, and finally locate the sound source.

[0040] Such as figure 1 Shown is the system block dia...

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 source localization method based on an acoustic bionic cochlea basal membrane, and relates to the field of speech recognition. According to the method, sound source localization is realized by employing an ear cocktail effect, the expandability is high, in the noise environment, compared with the conventional sound source localization method, the localization effect of the method is better, and the robustness of a sound source localization system is better. Spectrum analysis of sound source signals including noises is conducted via a cochlea basal membrane model, signal conversion is performed via an inner hair cell model on the cochlea basal membrane, cell superposition is performed via nerve fibers on the inner hair cells, voice information extraction is performed via a superior olivary nucleus model, and finally the localization of a sound source is realized.

Description

Technical field [0001] The present invention relates to the field of speech recognition, in particular to a sound source localization method with human auditory characteristics. Background technique [0002] The most important, most convenient, and fastest information exchange between people is language. The carrier of information in language is the sound signal, which is ubiquitous in life. The characteristics of loudness, frequency spectrum, and pitch in the sound signal can all reflect the characteristics of the direction and position of the sound signal. Therefore, many countries in the world have done a lot of research on sound signals and made great efforts. The voice interaction technology has gradually matured and the theory of various aspects has become more and more perfect. In the research of sound signal, the research of sound source localization technology is an extremely important aspect. The "cocktail party effect" fully demonstrated the speech separation and l...

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
IPC IPC(8): G10L15/02G01S5/20
CPCG10L15/02G01S5/20
Inventor 张毅徐晓东萧红罗久飞黄超苏祖强
Owner CHONGQING UNIV OF POSTS & TELECOMM
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