We propose a new algorithm for blind source separation (BSS), in which independent component analysis (ICA) and beamforming are combined to resolve the low-convergence problem through optimization in ICA. The proposed method consists of the following four parts: (1) frequency-domain ICA with direction-of-arrival (DOA) estimation, (2) null beamforming based on the estimated DOA, (3) diversity of (1) and (2) in both iteration and frequency domain, and (4) subband elimination (SBE) based on the independence among the separated signals. The temporal alternation between ICA and beamforming can realize fast- and high-convergence optimization. Also SBE enforcedly eliminates the subband components in which the separation could not be performed well. The experiment in a real car environment reveals that the proposed method can improve the qualities of the separated speech and word recognition rates for both directional and diffusive noises.
Cite as: Saruwatari, H., Sawai, K., Lee, A., Shikano, K., Kaminuma, A., Sakata, M. (2002) Speech enhancement in car environment using blind source separation. Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002), 1781-1784, doi: 10.21437/ICSLP.2002-262
@inproceedings{saruwatari02_icslp,
author={Hiroshi Saruwatari and Katsuyuki Sawai and Akinobu Lee and Kiyohiro Shikano and Atsunobu Kaminuma and Masao Sakata},
title={{Speech enhancement in car environment using blind source separation}},
year=2002,
booktitle={Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002)},
pages={1781--1784},
doi={10.21437/ICSLP.2002-262}
}