Title :
A convolutive blind signal separation method for joint speech signal separation and echo cancellation
Author :
Pan, Qiongfeng ; Aboulnasr, Tyseer
Author_Institution :
Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont.
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
Keywords :
blind source separation; convolution; echo suppression; higher order statistics; speech processing; convolutive blind signal separation; double talk phenomena; echo cancellation; higher-order statistics; speech signal separation; Adaptive filters; Blind source separation; Echo cancellers; Higher order statistics; Sensor systems; Signal processing; Signal processing algorithms; Source separation; Speech; Telephony;
Conference_Titel :
Circuits and Systems, 2003 IEEE 46th Midwest Symposium on
Conference_Location :
Cairo
Print_ISBN :
0-7803-8294-3
DOI :
10.1109/MWSCAS.2003.1562395
