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 Artificial Neural Network Based Non-Linear Filters

Amir Hussain, Douglas R. Campbell

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

In this paper, a new class of single-hidden layered linear-in-the-parameters, feedforward Artificial Neural Network (ANN) based adaptive non-linear filters is proposed for processing band-limited signals in a multi-microphone sub-band adaptive (MMSBA) speech enhancement system. Comparative results achieved in simulation experiments demonstrate that the proposed MMSBA system employing ANN based sub-band processing is capable of outperforming conventional noise cancellation schemes.

Full Paper

Bibliographic reference.  Hussain, Amir / Campbell, Douglas R. (1997): "A multi-microphone sub-band adaptive speech enhancement system employing artificial neural network based non-linear filters", In RSR-1997, 199-202.