Robust Speech Recognition for Unknown Communication Channels Pont-à-Mousson, France April 17-18, 1997

A Multi-Microphone Sub-Band Adaptive Speech Enhancement System Employing Diverse Sub-Band Processing

Amir Hussain, Douglas R. Campbell, Thomas J. Moir

Department of Electronic Engineering and Physics, University of Paisley, Paisley, Scotland, UK

A multi-microphone sub-band adaptive (MMSBA) speech enhancement system employing diverse sub-band processing is proposed. A technique based on the coherence function is developed in order to select the best form of processing within each sub-band. Comparative results achieved in simulation experiments demonstrate that the method is capable of outperforming conventional noise cancellation schemes.

Full Paper

Bibliographic reference.  Hussain, Amir / Campbell, Douglas R. / Moir, Thomas J. (1997): "A multi-microphone sub-band adaptive speech enhancement system employing diverse sub-band processing", In RSR-1997, 123-126.