Speech enhancement method for generating adversarial network based on two-dimensional spectrogram and conditions

A conditional generation and speech enhancement technology, applied in speech analysis, instruments, etc., can solve problems such as uncontrollability, and achieve the effect of strong robustness, good generalization performance, and improved score

Active Publication Date: 2020-01-21
SOUTHEAST UNIV
View PDF8 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Speech enhancement based on semi-supervised GAN (Generative Adversarial Nets) achieves end-to-end speech enhancement and improves the generalization performance of the algorithm. However, the GAN network belongs to semi-supervised learning and does not specify the corresponding label, resulting in generation Network G is relatively free and uncontrollable when processing large data

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 for generating adversarial network based on two-dimensional spectrogram and conditions
  • Speech enhancement method for generating adversarial network based on two-dimensional spectrogram and conditions
  • Speech enhancement method for generating adversarial network based on two-dimensional spectrogram and conditions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The technical solutions provided by the present invention will be described in detail below in conjunction with specific examples. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0053] Such as figure 1 As shown, the speech enhancement method based on two-dimensional spectrogram and conditional generative confrontation network provided by this embodiment includes the following steps:

[0054] Step 1, adding different types of noises with different signal-to-noise ratios in the training and testing speech signals to obtain noisy training and testing speech signals, the calculation formula is:

[0055] d(n)=s(n)+v(n)

[0056] Among them, d(n) represents the speech signal after adding noise, s(n) represents the monophonic speech signal, v(n) represents a certain type of noise signal under the specified signal-to-noise ratio, and n represent...

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 speech enhancement method for generating an adversarial network based on a two-dimensional spectrogram and conditions. The method comprises the following steps of forming thetwo-dimensional spectrogram through a plurality of frame spectrums obtained by performing short-time Fourier transform on a speech signal, generating input characteristics of the adversarial networkby serving the two-dimensional spectrogram as the condition, and generating a network G through the mutual adversarial training of a generating network G and a discrimination network D. In the testingprocess, the two-dimensional spectrogram of the noisy speech is extracted, and the G network obtained in the training stage directly maps the noisy speech spectrogram into an enhanced spectrogram, thereby realizing speech enhancement. Through the speech enhancement algorithm for generating the adversarial network based on the spectrogram and the conditions disclosed by the invention, the perception quality of the enhanced speech is greatly improved, and the algorithm has good generalization performance and stronger robustness.

Description

technical field [0001] The invention relates to a speech enhancement method based on a two-dimensional spectrogram and a conditional generation confrontation network, and belongs to the technical field of speech enhancement. Background technique [0002] Speech enhancement refers to the technology that the speech signal is interfered or suppressed by noise, and the effective signal is extracted from the background noise. Its purpose is to eliminate the influence of noise and interference as much as possible, improve the signal-to-noise ratio and speech intelligibility, and improve speech quality. Speech enhancement technology can improve the overall performance of the speech signal processing system. [0003] Currently, there are many kinds of speech enhancement algorithms, which can be classified according to different classification standards. According to the number of sensors or microphones, it can be divided into single-channel (single-microphone) speech enhancement an...

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): G10L21/0208G10L25/27
CPCG10L21/0208G10L25/27
Inventor 周琳钟秋月陆思源李楠
Owner SOUTHEAST UNIV
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