Voice signal enhancing method and device

A voice signal and enhancement device technology, applied in voice analysis, neural learning methods, biological neural network models, etc., can solve problems such as additional noise, limited effects and application scenarios, signal distortion, etc., to reduce signal distortion and improve speech. The effect of the signal booster effect

Inactive Publication Date: 2019-07-12
XIAMEN YEALINK NETWORK TECH
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the existing technology is used for speech signal enhancement, it is found that these speech signal enhancement methods are artificial preset methods in principle, so the effects and application scenarios are limited by the preset methods and method designers, and the actual speech scene Various, in the process of using the existing technology for speech enhancement, signal distortion and additional noise will inevitably occur. Therefore, in the face of complex speech scenes, the robustness of the existing speech enhancement technology is relatively low. Difference

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 signal enhancing method and device
  • Voice signal enhancing method and device
  • Voice signal enhancing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0038] See figure 1 .

[0039] see figure 1 , is a schematic flow chart of a speech signal enhancement method provided by an embodiment of the present application, such as figure 1 As shown, the speech signal enhancement method includes:

[0040] Step S11, collecting the voice signal of the current scene.

[0041] Since the sound source with a sampling frequency of 22.05KHz has reached the sound quality of FM radio, it can be clearly identified. If the sound source above 22.05KH...

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 signal enhancing method and a voice signal enhancing device. The method comprises the following steps: segmenting voice signals of the current scene into a plurality offrame signals based on the preset duration interval; based on the preset step size, inputting the plurality of frame signals into a trained neural network, and carrying out convolution operation on the plurality of frame signals through a convolution layer in skipping connection, thus obtaining the plurality of enhanced frame signals; and according to the time domain of each enhanced frame signal, superposing the enhanced frame signals, thus obtaining the enhanced voice signal. Compared with the prior art, the technical scheme has the beneficial effects that the neural network is used for carrying out automatic enhancement on the voice signal, the manual intervention is not needed, so that the effect of voice enhancement and the application scene are not limited by a preset method and a method designer, therefore, the occurrence frequency of signal distortion and additional noise is reduced, and further, the enhancing effect of the voice signal is improved.

Description

technical field [0001] The present application relates to the technical field of speech signal processing, in particular to a speech signal enhancement method and device. Background technique [0002] Speech signal enhancement is to improve the intelligibility of speech and to enhance the speech polluted by additive noise. It is mainly used in communication equipment, and also in hearing aids, cochlear implants and other implanted devices. The existing speech signal enhancement methods usually use "spectral subtraction", "Wiener filter", "statistical model method", "subspace method" and so on. However, when the existing technology is used for speech signal enhancement, it is found that because these speech signal enhancement methods are artificial preset methods in principle, the effects and application scenarios are limited by the preset methods and method designers, and the actual speech scene Various, in the process of using the existing technology for speech enhancement...

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): G10L21/02G10L25/30G10L25/45
CPCG10L21/02G10L25/30G10L25/45G10L21/0208G10L21/0232G06N20/00G06N3/08G10L21/0272
Inventor 冯万健张联昌刘键涛
Owner XIAMEN YEALINK NETWORK 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