In this paper we address the problem of using two or more microphones to enhance speech corrupted by nonstationary noise, such as that of a competing speaker (cocktail party effect) at very low SNR, by means of linear filtering of two microphone signals. This work is a variant to the probabilistic Independent Component Analysis (ICA) method but using a more accurate probability distribution of the speech signal based on a mixture Autoregressive model. Comparison with other algorithms on published real recordings shows more separation than with previously existing ICA algorithms.
Cite as: Acero, A., Altschuler, S., Wu, L. (2000) Speech/noise separation using two microphones and a VQ model of speech signals. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 532-535
@inproceedings{acero00b_icslp,
author={Alex Acero and Steven Altschuler and Lani Wu},
title={{Speech/noise separation using two microphones and a VQ model of speech signals}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 532-535}
}