Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Single-channel monitor-free voice and noise separating method based on low-rank and sparse matrix decomposition

A technology of sparse matrix and separation method, which is applied in speech analysis, instruments, etc., can solve the problems of restricting the application of algorithms, and achieve the effect of improving speech quality and great practical value

Active Publication Date: 2014-07-30
PLA UNIV OF SCI & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since most of the current speech-noise separation algorithms rely on prior knowledge, that is, they need to be trained on speech or noise data in advance, this feature limits the application of these algorithms in practical situations

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
  • Single-channel monitor-free voice and noise separating method based on low-rank and sparse matrix decomposition
  • Single-channel monitor-free voice and noise separating method based on low-rank and sparse matrix decomposition
  • Single-channel monitor-free voice and noise separating method based on low-rank and sparse matrix decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] Figure 4 It is a schematic diagram of speech-noise separation for a piece of noisy speech data, where the speech sampling rate is 8KHz, the frame-dividing time window length L is 256, and the frame shift R is 128. When performing discrete Fourier transform on each frame, the number of frequency points K=256, when performing low-rank and sparse matrix decomposition on the time spectrum of noisy speech, the value of r is 2, and the value of c is 3000. It can be seen from the figure that after the speech-noise separation of the noisy speech y(n) by this method, the noise interference can be eliminated to a great extent and a pure speech can be obtained

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 single-channel monitor-free voice and noise separating method based on low-rank and sparse matrix decomposition. The method includes the steps of converting a time domain waveform of noise-contained voice to a time frequency domain via short-time Fourier transform to obtain a magnitude spectra with noises; decomposing the magnitude spectra with the noises into a sum of a noise magnitude spectra, a voice magnitude spectra and a residual noise magnitude spectra by a low-rank and sparse matrix decomposition algorithm; and finally reconstructing a voice time-domain waveform from the voice magnitude spectra via short-time Fourier transform. Without any priori information about voice and noise, the method is the single-channel monitor-free voice and noise separating method, pure voice can be separated from noise-contained voice by the aid of an algorithm, and the single-channel monitor-free voice and noise separating method is simple, effective, and particularly suitable for voice extraction in strong-noise environment.

Description

technical field [0001] The invention belongs to the technical field of speech signal processing, and relates to a speech noise separation method, in particular to a single-channel unsupervised speech noise separation method based on low-rank and sparse matrix decomposition. Background technique [0002] Speech and noise separation is the processing of noisy speech in order to separate the target speaker's speech in a complex noise environment. The main goal is to eliminate the interference of environmental noise on speech and improve speech quality. Speech-to-noise separation can be said to be an extension of the Speech Enhancement algorithm, and the noise it processes can even include the voices of other speakers. [0003] In the last century, due to the limitations of computer computing power, people focused their attention on single-channel speech enhancement or speech denoising algorithms with low algorithm complexity and easy implementation. Typical of this type of alg...

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 Patents(China)
IPC IPC(8): G10L21/0224G10L21/0272G10L25/45
Inventor 张雄伟黄建军吴海佳贾冲曾理周彬
Owner PLA UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products