Speech enhancement method based on multi-head self-attention mechanism

A speech enhancement and attention technology, applied in speech analysis, instruments, etc.

Active Publication Date: 2020-01-31
BEIJING INST OF COMP TECH & APPL
View PDF8 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is: how to suppress the noise part during the operation of the attention mechanism and improve the speech enhancement performance

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 based on multi-head self-attention mechanism
  • Speech enhancement method based on multi-head self-attention mechanism
  • Speech enhancement method based on multi-head self-attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the purpose, content, and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0039] The current speech enhancement method based on the attention mechanism amplifies the clean speech information and the noise information at the same time in the process of applying the attention mechanism, and does not obviously suppress the noise part. To solve this problem, the present invention proposes a speech enhancement method based on a multi-head self-attention mechanism. Due to the masking effect in the process of human auditory perception, the signal with lower energy will be masked by the signal with higher energy. According to this effect, by applying multi-head self-attention operation on the continuous input of adjacent multi-frame speech features, calculating the similarity between each input fram...

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 relates to a speech enhancement method based on a multi-head self-attention mechanism and relates to the technical field of speech enhancement. According to the method, for the problem that noises cannot be clearly suppressed in an attention computing process through adoption of the speech enhancement method based on an attention mechanism, on the basis of research and utilization ofmasking effect existing in an auditory perception process of people, the invention provides the speech enhancement method based on the multi-head self-attention mechanism. According to the method, the part of suppressing noises in the attention mechanism computing process is realized, and speech enhancement performance is improved.

Description

technical field [0001] The invention relates to the technical field of speech enhancement, in particular to a speech enhancement method based on a multi-head self-attention mechanism. Background technique [0002] Speech enhancement technology, as a basic link in the signal processing process, has broad application prospects in many fields such as speech recognition, mobile communication and artificial hearing. Its main purpose is to improve the quality and intelligibility of speech polluted by noise. Recently, with the rise of deep learning technology, supervised speech enhancement methods based on deep neural networks (Deep Neural Network, DNN) have achieved great success, especially in the case of low SNR and non-stationary noise, compared to Traditional methods show more powerful advantages. [0003] Compared with machines, humans can ignore the interference of background noise and hear the other party's voice when chatting with others in a noisy environment. This is ...

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): G10L21/0208G10L25/27G10L25/03
CPCG10L21/0208G10L25/27G10L25/03
Inventor 常新旭袁晓光张杨寇金桥杨林吴敏王昕徐冬冬赵晓燕闫帅
Owner BEIJING INST OF COMP TECH & APPL
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