Directional voice enhancement method and system

A directional enhancement and speech technology, applied in speech analysis, instruments, etc., can solve the problems of inability to deal with sudden changes of noise, poor target direction accuracy, etc., to achieve high clarity/intelligibility, large noise attenuation, and good noise reduction. effect of effect

Active Publication Date: 2020-12-01
AISPEECH CO LTD
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to at least solve the problems in the existing technology that cannot deal with sudden noise, the accuracy of the target direction is poor in the presence of environmental noise, and the need for voice wake-up and other limitations

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
  • Directional voice enhancement method and system
  • Directional voice enhancement method and system
  • Directional voice enhancement method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0065] As an implementation manner, the microphone array using m microphones to divide the space into n intervals includes:

[0066] Based on the designated space preset by the user, a microphone array of m microphones is used to divide the space into n equally divided or n unequally divided intervals.

[0067] In this implementation manner, these directions may be equally divided by 360°, or filter weights may be designed for unequal divisions according to actual requirements. For example, the anchor mentioned above. Since the location of the anchor is relatively fixed, this can be divided into unequal spaces, and the spatial angle division of the location of the anchor is larger. In this way, the clarity and intelligibility of speech are further improved in the specified direction relative to the microphone array.

[0068] Such as image 3 Shown is a schematic structural diagram of a directional speech enhancement system provided by an embodiment of the present invention,...

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 embodiment of the invention provides a directional voice enhancement method. The method comprises the following steps: dividing a space into n intervals by using a microphone array of m microphones, and performing signal directional enhancement on the n intervals; collecting voice signals of n channels in the n intervals; and inputting the voice signals of the n channels into a channel selection module, determining the parameter sizes of the voice signals of the n channels based on a neural network if no specified voice reception interval exists, determining a directional voice reception interval in the n intervals, and determining the voice signals of the channels corresponding to the directional voice reception interval as enhanced directional voice. The embodiment of the invention also provides a directional voice enhancement system. According to the embodiment of the invention, the problem of performance reduction possibly caused by DOA calculation is avoided, and a better noise reduction effect can be obtained by utilizing the advantage that the neural network is superior to a traditional noise estimation algorithm.

Description

technical field [0001] The invention relates to the field of speech enhancement, in particular to a method and system for enhancing directional speech. Background technique [0002] In order to improve the effect of voice collection and recognition, the location of the target source's speech will be taken into consideration for directional pickup. Usually used: 1. Obtain the required angle through directional pickup instructions, then compensate for the delay, and then reduce the noise through the preset filter algorithm. The noise estimation method is the optimal estimation method of logarithmic spectrum amplitude and / or MCRA Algorithm; 2. Obtain the general direction of the target sound source through the TDOA method, and then calculate the weighted vector of the target sound source by MVDR, and finally obtain the directional pickup data at the exact position of the target sound source; 3. Through the wake-up function of the smart device and the multi- An instantaneous di...

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): G10L21/0208G10L21/0216G10L25/30
CPCG10L21/0208G10L21/0216G10L25/30G10L2021/02166
Inventor 周晨
Owner AISPEECH CO LTD
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