Speech enhancement method based on non-negative low-rank and sparse matrix decomposition principle

A sparse matrix and speech enhancement technology, applied in the field of signal processing, can solve problems such as decomposition errors and affecting the quality of speech and hearing, and achieve a robust effect

Inactive Publication Date: 2014-02-05
KEY LAB OF SCI & TECH ON AVIONICS INTEGRATION TECH
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Negative magnitude spectrum not only causes decomposition errors, but also produces music noise that is uncomfortable for the human ear, thus affecting the quality of speech hearing

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 non-negative low-rank and sparse matrix decomposition principle
  • Speech enhancement method based on non-negative low-rank and sparse matrix decomposition principle
  • Speech enhancement method based on non-negative low-rank and sparse matrix decomposition principle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described now in conjunction with accompanying drawing, see figure 1 , a speech enhancement method based on non-negative low-rank and sparse matrix factorization principles, including the following specific steps:

[0036]1) Perform preprocessing 101 on the noisy speech signal y(t); the stage of preprocessing 101 includes signal smoothing and framing to facilitate subsequent processing. Signal smoothing refers to the calculation of the current value of the noisy speech signal by using the mean value of the nearest neighbor signal at point P of y(t) to smooth the amplitude waveform of the noisy speech signal. The value of P among the present invention is 3, namely The window function used for framing is the Hamming window, the window length is 200 points, and the number of overlapping points for each frame movement is 80 points;

[0037] 2) DFT (Discrete Fourier Transform) 102 is performed on the noisy speech signal after framing ...

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 based on the non-negative low-rank and sparse matrix decomposition principle. The method includes the first step of firstly carrying out smoothing, framing and discrete Fourier transformation on noisy speech signals to obtain noisy speech frequency spectra, the second step of allowing the noisy speech magnitude spectra of frames to serve as column vectors which are arranged in chronological order to form a noisy speech time-frequency matrix and then carrying out non-negative low-rank and sparse matrix decomposition on the noisy speech time-frequency matrix to obtain a non-negative low-rank and sparse matrix, and the third step of utilizing the sparse matrix and reconstruction of noisy speech phase positions to enhance the speech spectra and finally obtaining the enhanced speech in a time domain form through inverse Fourier transformation. By the adoption of the method, noise adaptability is high, endpoint detection and model training are not needed, parameters are fewer and easy to regulate, strong noise environmental performance is good, and therefore the method has a good application prospect.

Description

technical field [0001] The invention relates to the field of signal processing and is suitable for noise suppression of noisy speech, in particular a speech enhancement method based on non-negative low rank and sparse matrix decomposition principles. Background technique [0002] Speech signal is the most natural and effective means for human beings to exchange information. As mankind enters the information age, it is urgent to use advanced speech processing technology to promote the intelligence of human society. As early as 2000, Bill Gates once proposed that "the next 10 years will be the era of voice". In recent years, as companies such as Apple, Google, and Microsoft successively launched intelligent voice services, the intelligent voice industry has become an emerging industry in the field of information technology, and user awareness and market size are gradually expanding. In particular, Apple's newly launched smart phone has the voice assistant function, and iFLYT...

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): G10L21/0232G10L21/0272
Inventor 孙成立须明王希敏谢坚筱
Owner KEY LAB OF SCI & TECH ON AVIONICS INTEGRATION 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

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