Method, apparatus and equipment for establishing voice enhancement network and computer storage medium

A voice enhancement and network technology, applied in voice analysis, neural learning methods, biological neural network models, etc., can solve problems such as unstable convergence of generative confrontation networks, loss of voice spectrum, and too clear generation, so as to enhance stability and improve Performance, Accuracy Improvement Effects

Active Publication Date: 2019-01-04
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Through the research, it is found that when the existing training method is used to train the GAN, although it can accelerate the convergence of the GAN training, it will lead to the instability of the GAN convergence, which wi

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
  • Method, apparatus and equipment for establishing voice enhancement network and computer storage medium
  • Method, apparatus and equipment for establishing voice enhancement network and computer storage medium
  • Method, apparatus and equipment for establishing voice enhancement network and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0033] Terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. As used in the embodiments of the present invention and the appended claims, the singular forms "a", "said" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0034] It should be understood that the term "and / or" used herein is only an association relationship describing associated objects, which means that there may be three relationships, for example, A and / or B, which may mean that A exists alone, and A and B exist simultaneously. B, there are three situations of B alone. In addition, the character " / " in this articl...

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 method, an apparatus and equipment for establishing a voice enhancement network and a computer storage medium. The method comprises the following steps: obtaining a noisy speech spectrum and a clear speech spectrum corresponding to each noisy speech spectrum as training samples; obtaining a noisy speech spectrum corresponding to each noisy speech spectrum as training samples. constructing a generation antagonism network including a generator and a discriminator; according to the obtained noisy speech spectrum and the corresponding clear speech spectrum, training the generated antagonistic network by switching the loss function of the generator in N training stages, and obtaining the speech enhancement network by using the generator in the generated antagonistic network obtained by training, wherein N is a positive integer greater than or equal to 2. The invention can enhance the stability of the training convergence of the generated antagonistic network, thereby improving the performance of the speech enhancement network based on the generated antagonistic network, and further realizing the purpose of improving the accuracy of speech recognition.

Description

【Technical field】 [0001] The invention relates to speech recognition technology, in particular to a method, device, equipment and computer storage medium for establishing a speech enhancement network. 【Background technique】 [0002] Speech recognition in a noisy environment has always been an urgent problem in the field of speech recognition. The current mainstream method is to add a speech enhancement network in front of the speech recognition system. So far, Generative Adversarial Network (GAN) is the latest enhancement method as a speech enhancement network. Through the research, it is found that when the existing training method is used to train the GAN, although it can accelerate the convergence of the GAN training, it will lead to the instability of the GAN convergence, which will make the generator in the GAN generate too clear Speech spectrum, resulting in the loss of some subtle but important information in the speech spectrum in the existing speech enhancement net...

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): G10L21/02G10L21/0232G10L25/30G06N3/04G06N3/08
CPCG06N3/08G10L21/02G10L21/0232G10L25/30G06N3/045
Inventor 成学军
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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