An Efficient Switching Mechanism Using Voice Activity Detection for Acoustic Echo Cancellation

DOI

10.2991/icmmct-16.2016.246How to use a DOI?

Keywords

AEC, VAD, APA, NLMS

Abstract

Adaptive algorithms are widely used for acoustic echo cancellation (AEC). In this paper, an efficient switching tactic with advantageous features of NLMS and APA is proposed for AEC application. Switching points are decided by employing a smart voice activity detection scheme based on speech utterance. The speech signal is distinguished as voiced, unvoiced and silent periods then switch mechanism will automatically assign algorithm, either NLMS or APA, to the corresponding period. The prime motive of this proposed switch algorithm is to reduce the computational complexity and get better output over the NLMS but close to APA. Simulation results show the performance of proposed scheme is significantly improved.

Copyright

© 2016, 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  - A.A.M. Muzahid
AU  - S.I.M.M. Raton Mondol
AU  - K.M.R. Ingrid
AU  - Y. Zhou
PY  - 2016/03
DA  - 2016/03
TI  - An Efficient Switching Mechanism Using Voice Activity Detection for Acoustic Echo Cancellation
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 1254
EP  - 1258
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.246
DO  - 10.2991/icmmct-16.2016.246
ID  - Muzahid2016/03
ER  -