A Speech denoising method Based on wavelet threshold and improved spectral subtraction

DOI

10.2991/iccsee.2013.203How to use a DOI?

Keywords

Wavelet transform, Speech de-noising, Spectral subtraction

Abstract

In the speech de-noising method, wavelet threshold method and the spectral subtraction with simple algorithm and good performance has attracted the attention of many researchers. Based on the traditional spectral subtraction, the author found that the speech signal non-stationary noise cannot be effectively restrained, therefore, the improved algorithm based on wavelet threshold value and improved spectral subtraction is proposed The Experimental results show that this method in low signal-to-noise ratio, can effectively restrain "music noise", enhance the signal to noise ratio (SNR) and improve the quality of speech.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ling Wei
AU  - Li Wang
PY  - 2013/03
DA  - 2013/03
TI  - A Speech denoising method Based on wavelet threshold and improved spectral subtraction
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 804
EP  - 807
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.203
DO  - 10.2991/iccsee.2013.203
ID  - Wei2013/03
ER  -