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

Speech enhancement method and system based on microphone array

A microphone array and voice enhancement technology, which is applied in voice analysis, instruments, etc., and can solve the problems of enhancement effects and other issues

Active Publication Date: 2019-12-06
SHANGHAI KEYGO TECH CO LTD
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the enhancement effect of such techniques will be greatly affected when part of the speech signal components leak into the reference noise path

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
  • Speech enhancement method and system based on microphone array
  • Speech enhancement method and system based on microphone array
  • Speech enhancement method and system based on microphone array

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Such as figure 1 As shown, the present embodiment relates to a speech signal enhancement method, comprising the following steps:

[0027] S1: Calibrate the relative transfer function (RTF) between each microphone through the camera, the specific steps include:

[0028] S1.1 Set the signal source at 20 different positions within the range of the camera screen at a distance of 1 meter from the array and send out chirp signals with a frequency range of 200-4000 Hz for 1 second, and record the pixel points in the image where each occurrence occurs.

[0029] S1.2 Calculate the angle between the sound source and the array through the pixel where the sound source is located.

[0030] S1.3 Calculate the theoretical transfer function of each microphone relative to the reference microphone through the coordinate position of each microphone on the microphone array and the included angle of the sound source.

[0031] Such as figure 2 It is the distribution diagram of the microp...

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 speech enhancement method and system based on a microphone array. The speech enhancement method includes the steps of calibrating relative transfer functions between each of microphones according to video images, obtaining a noise distribution situation within a monitoring scope through a sound pressure distribution diagram and correspondingly using speech enhancement algorithm or noise suppression algorithm to carry out merged processing on collected signals by the microphone array, and finally, using an equalizer based on minimum norm p algorithm to process and obtain enhanced speech signals. The speech enhancement method and system can be used for achieving multi-channel microphone speech enhancement and noise reduction and the system can run separately from computers so as to facilitate camouflage.

Description

technical field [0001] The present invention relates to a technology in the field of speech processing, in particular to a microphone array-based speech enhancement method and system. Background technique [0002] Most of the existing speech enhancement schemes are based on a small number of microphones. Common ones are smart speakers based on wake-up words. This type of application is used in relatively fixed occasions, and the environmental noise is relatively small. In the field of listening, the listening object is far away, and the signal-to-noise ratio of the voice signal decreases rapidly. Taking into account factors such as environmental noise and reverberation, ordinary microphone array voice processing technology is used to perform far-field voice processing through beamforming and other methods. Enhanced performance is not ideal. [0003] Some improved technologies improve the signal-to-noise ratio of the signal channel by adding an adaptive processor to the fix...

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): G10L21/0216
CPCG10L21/0216G10L2021/02166
Inventor 张南雄李宏斌
Owner SHANGHAI KEYGO TECH CO LTD
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