A binaural sound source localization method based on deep learning in digital hearing aids

A deep learning and sound source localization technology, applied in hearing aids, localization, and devices for obtaining desired pointing characteristics, etc., can solve the problems of inability to meet the real-time performance of hearing aids and high technical complexity of sound source localization

Active Publication Date: 2021-05-14
BEIJING UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For most digital hearing aids, the sound source localization technology is highly complex and causes time delay, which cannot meet the real-time requirements of hearing aids

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
  • A binaural sound source localization method based on deep learning in digital hearing aids
  • A binaural sound source localization method based on deep learning in digital hearing aids
  • A binaural sound source localization method based on deep learning in digital hearing aids

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Step 1. Using the human auditory perception theory, combining the auditory characteristics of the human ear and the working mechanism of the cochlea, pass the binaural speech signal into the gammatone filter and divide it into N channels, and extract the sensitive information of the human ear;

[0021] Due to the frequency division characteristics and auditory masking characteristics of the cochlea, the gammatone filter bank is used to decompose the speech signal into multiple channels. The gammatone filter is a cochlear basement membrane model based on the auditory model, which can better simulate the sharpness of the basement membrane. The filter characteristics of the filter are in line with the auditory perception characteristics of the human ear, and the realization of the filter is simple. Therefore, the gammatone filter bank is selected to decompose the signal of the noisy speech, so that it can simulate the auditory characteristics of the human ear. The time-doma...

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 binaural sound source localization method based on deep learning in a digital hearing aid. First, binaural sound source signals are decomposed into several channels through a gammatone filter, and high-energy channels are extracted through weighting coefficients, and then the head correlation function ( head‑related‑transform function, HRTF) extracts the first type of features, that is, Interaural Time Difference (Interaural Time Difference, ITD) and Interaural Intensity Difference (Interaural Intensity Difference, IID) as the input of deep learning, and divides the horizontal plane into four Quadrant to narrow down the targeting. Then extract the second type of features of head-related transmission, namely, the interaural level difference (Interaural Level Difference, ILD) and the interaural phase difference (Interaural Phase Difference, IPD). Finally, in order to obtain more accurate positioning, the first type and The four features of the second category are used as the input of the next deep learning, so as to obtain the azimuth angle of the sound source localization. Realize the precise positioning of 72 azimuth angles from 0° to 360° on the horizontal plane with a step size of 5°.

Description

technical field [0001] The invention belongs to the technical field of speech signal processing, and relates to a binaural sound source localization method based on deep learning in a digital hearing aid. Background technique [0002] Deafness has become a worldwide problem. For the deaf, choosing suitable digital hearing aids is the best way to help them improve their hearing. The basic working principle of digital hearing aids is as follows: figure 2 As shown, the external sound signal enters the microphone to convert sound energy into electrical energy, and then converts it into a digital signal through an analog / digital converter, and then uses a multi-channel loudness compensation algorithm, adaptive noise reduction algorithm, and echo cancellation algorithm in the DSP processor , frequency shifting algorithm and sound source localization and other technologies for processing, the processed digital electrical signal needs to be converted into an analog electrical sign...

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): G10L19/26G10L21/0264G10L25/06G10L25/30H04R25/00G01S5/20
CPCG01S5/20G10L19/26G10L21/0264G10L25/06G10L25/30H04R25/40
Inventor 李如玮潘冬梅李涛刘亚楠张永亚
Owner BEIJING UNIV OF TECH
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