BINAURAL SUBBAND ADAPTIVE SPEECH ENHANCEMENT USING ARTIFICIAL NEURAL NETWORKS

Authors
HUSSAIN A CAMPBELL DR
Citation
A. Hussain et Dr. Campbell, BINAURAL SUBBAND ADAPTIVE SPEECH ENHANCEMENT USING ARTIFICIAL NEURAL NETWORKS, Speech communication, 25(1-3), 1998, pp. 177-186
Citations number
28
Categorie Soggetti
Communication,"Computer Science Interdisciplinary Applications","Computer Science Interdisciplinary Applications",Acoustics
Journal title
Speech communication → ACNP
ISSN journal
01676393
Volume
25
Issue
1-3
Year of publication
1998
Pages
177 - 186
Database
ISI
SICI code
0167-6393(1998)25:1-3<177:BSASEU>2.0.ZU;2-X
Abstract
In this paper, a general class of ''single-hidden layered, feedforward '' Artificial Neural Network (ANN) based adaptive non-linear filters i s proposed for processing band-limited signals in a multi-microphone s ub-band adaptive speech-enhancement scheme. Initial comparative result s achieved in simulation experiments using both simulated and real aut omobile reverberant data demonstrate that the proposed speech-enhancem ent system employing ANN-based sub-band processing is capable of outpe rforming conventional noise cancellation schemes. (C) 1998 Elsevier Sc ience B.V. All rights reserved.