Speech Signal Enhancement Method Based on Group Sparse Low-Rank Representation
A voice signal and group sparse technology, applied in voice analysis, instruments, etc., can solve problems such as noise, and achieve the effect of eliminating background noise and quickly and accurately understanding
Active Publication Date: 2017-04-12
ZHEJIANG UNIV
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Then, due to the constraints of various objective environmental conditions, such as the crying of children at home, the noise of vehicles outside the meeting room, the sound of machines running in the laboratory, and the sound of bombs in war, etc., the voice signal collected by the audio equipment Usually accompanied by varying degrees of noise
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] With reference to accompanying drawing, further illustrate the present invention:
[0025] A speech signal enhancement method based on group sparse low-rank expression, the method includes the following steps:
[0026] 1. After obtaining a large number of noisy speech signals of different topics, perform the following operations on the noisy speech signals:
[0027] 1) According to the preset sampling frequency f s Sampling each noisy speech signal to obtain an m-dimensional vectorized representation x∈R m , and group the speech signals according to different themes;
[0028] 2) Utilizing the group-sparse structural characteristics of the speech signals of the same topic, the noise separation of the noisy speech signals is realized through low-rank matrix decomposition, and the group-sparse low-rank expression of the speech signals is obtained;
[0029] 3) Reconstruct the original noisy signal through the obtained low-rank expression, so as to output a clear enhanced...
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
Login to View More Abstract
The invention provides a speech signal enhancing method based on a group sparse low-rank expression. The following operations are carried out for voice signals with noise: firstly, the voice signals are sampled according to a preset sampling frequency, corresponding quantitative expressions are formed, and the voice signals are grouped according to different subjects; secondly, by using a group sparse structure characteristic between voice signals with the same subject, the voice signals with noise are separated through low-rank matrix decomposition, and the group sparse low-rank expression of the voice signals is obtained; finally through the obtained low-rank expression, the original signal with noise are reconstructed, and a clear enhanced voice signal is obtained. The method has the advantages that the group sparse structure characteristic between the voice signals with the same subject is effectively considered, the background noise can be eliminated well and the clear voice signal is obtained, thus a listener rapidly and correctly understands the voice content, and the method can be applied to military communication, network audio conferencing, online radio broadcasting and the like.
Description
technical field [0001] The invention relates to the technical field of speech signal enhancement, in particular to a speech signal enhancement method based on group sparse low-rank expression. Background technique [0002] With the popularization of digital media devices in people's daily work and life, especially the rapid development of Internet technology, massive voice data is generated every day, and these data have a vital impact on communication and cooperation in many fields in real life . Then, due to the constraints of various objective environmental conditions, such as the crying of children at home, the noise of vehicles outside the meeting room, the sound of machines running in the laboratory, and the sound of bombs in war, etc., the voice signal collected by the audio equipment Usually accompanied by varying degrees of noise. Therefore, how to effectively separate the noise components in the speech data and enhance the speech signal is a problem that is of gr...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L21/0208G10L21/0272
Inventor 李平卜佳俊陈纯高珊王学庆
Owner ZHEJIANG UNIV