Speech Enhancement in Presence of Colored Noise Using An Improved Least Square Estimation

DOI

10.2991/icmt-13.2013.96How to use a DOI?

Keywords

Colored noise, noisy speech signal, speech enhancement, parametric method

Abstract

Speech enhancement in presence of colored noise has been of signi¯cant topics. This pa-per presents a novel parameter estimation-based method for speech enhancement under colored noise environments. Parameters of speech signal modeled as autoregressive process are estimated by using an improved least square estimation and then the speech signal is recovered from the Kalman ¯ltering. Compared with the adaptive recursive estimation-based method for speech enhancement, the present method has a low computation complexity. Moreover, computed results shows that the presented para-metric method has a better performance in having a signi¯cant gain in SNR than the adaptive recursive estimation-based method at di®erent colored noise.

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  - Xia Youshen
AU  - Wang Pengyu
PY  - 2013/11
DA  - 2013/11
TI  - Speech Enhancement in Presence of Colored Noise Using An Improved Least Square Estimation
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 772
EP  - 779
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.96
DO  - 10.2991/icmt-13.2013.96
ID  - Youshen2013/11
ER  -