A convolutive blind signal separation method for joint speech signal separation and echo cancellation

TitleA convolutive blind signal separation method for joint speech signal separation and echo cancellation
Publication TypeConference Paper
Year of Publication2003
AuthorsPan, Q., and T. Aboulnasr
Conference NameMicro-NanoMechatronics and Human Science, 2003 IEEE International Symposium on
Pagination752 -755 Vol. 2
Date Publisheddec.
Keywordsblind source separation, convolution, convolutive blind signal separation, double talk phenomena, echo cancellation, echo suppression, higher order statistics, higher-order statistics, speech processing, speech signal separation
Abstract

In this paper, we construct a unified blind signal separation model for network and acoustic echo cancellation and propose using a convolutive blind signal separation method based on higher-order statistics to perform joint speech signal separation and echo cancellation. The advantage of this approach is that it works well in the presence of double talk which seriously affects the performance of conventional echo cancellers. The performance is verified by simulation results

URLhttp://dx.doi.org/10.1109/MWSCAS.2003.1562395
DOI10.1109/MWSCAS.2003.1562395

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia