In this paper, we propose a novel implementation of a minimax decision rule for continuous density hidden Markov model based robust speech recognition. By combining the idea of the minimax decision rule with a normal Viterbi search, we derive a recursive minimax search algorithm, where the minimax decision rule is repetitively applied to determine the partial paths during the search procedure. Because of its intrinsic nature of a recursive search, the proposed method can be easily extended to perform continuous speech recognition. Experimental results on Japanese isolated digits and TIDIGITS, where the mismatch between training and testing conditions is caused by additive white Gaussian noise, show the viability and efficiency of the proposed minimax search algorithm.
Cite as: Jiang, H., Hirose, K., Huo, Q. (1998) A minimax search algorithm for CDHMM based robust continuous speech recognition. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0693, doi: 10.21437/ICSLP.1998-304
@inproceedings{jiang98_icslp,
author={Hui Jiang and Keikichi Hirose and Qiang Huo},
title={{A minimax search algorithm for CDHMM based robust continuous speech recognition}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0693},
doi={10.21437/ICSLP.1998-304}
}