In this paper, a wavelet transform domain realization of the blind equalization technique termed as EVA is applied to speech analysis. The conventional linear prediction problem can be viewed as a constrained blind equalization problem. Because the EVA does not impose any restriction to the probability distribution in the input (the glottal excitation), the principal features of speech can be effectively separated from a speech in a short duration. The computational complexity will be a problem, but the proposed implementation in a wavelet transform domain promotes the faster convergence in the analysis of speech signal.
Cite as: Namba, M., Ishida, Y. (1998) Wavelet transform domain blind equalization and its application to speech analysis. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0055, doi: 10.21437/ICSLP.1998-542
@inproceedings{namba98_icslp,
author={Munehiro Namba and Yoshihisa Ishida},
title={{Wavelet transform domain blind equalization and its application to speech analysis}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0055},
doi={10.21437/ICSLP.1998-542}
}