An adaptive sub-band multisensor structure for speech enhancement is proposed, its conceptual basis being the accepted model of the cochlea as a spectrum analyser. The convergence of the proposed method is compared with conventional LMS and frequency domain LMS and a dramatic increase in convergence rate is shown using both simulated and real data.
Cite as: Toner, E., Campbell, D.R. (1992) Speech enhancement based conceptually on auditory processing. Proc. ETRW on Speech Processing in Adverse Conditions, 151-154
@inproceedings{toner92_spac,
author={E. Toner and D. R. Campbell},
title={{Speech enhancement based conceptually on auditory processing}},
year=1992,
booktitle={Proc. ETRW on Speech Processing in Adverse Conditions},
pages={151--154}
}