To improve the robustness of speech recognition in additive noisy environments, an SVD based space transformation approach is proposed. It is shown that with this approach, not only the signal-to-noise ratio is improved but also a significant recognition error reduction is achieved. A multiple model based on the proposed method is developed and it can provide high recognition rate for a large range of SNRs. Recognition experiments on a speaker-dependent mono-syllabic database with additive noise show that, this new approach outperforms LPC cepstrum, MFCC, and OSALPC cepstrum significantly.
Cite as: Guan, C.-t., Leung, S.-h., Lau, W.-h. (1997) A space transformation approach for robust speech recognition in noisy environments. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1591-1594, doi: 10.21437/Eurospeech.1997-456
@inproceedings{guan97_eurospeech,
author={Cun-tai Guan and Shu-hung Leung and Wing-hong Lau},
title={{A space transformation approach for robust speech recognition in noisy environments}},
year=1997,
booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
pages={1591--1594},
doi={10.21437/Eurospeech.1997-456}
}