Weighted Viterbi algorithm and state duration modelling for speech recognition in noise

N.B. Yoma, F.R. McInnes, M.A. Jack
Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)  
A weighted Viterbi algorithm (HMM) is proposed and applied in combination with spectral subtraction and Cepstral Mean Normalization to cancel both additive and convolutional noises in speech recognition. The weighted Viterbi approach is compared and used in combination with state duration modelling. The results presented in this paper show that a proper weight on the information provided by static parameters can substantially reduce the error rate, and that the weighting procedure improves
more » ... edure improves better the robustness of the Viterbi algorithm than the introduction of temporal constraints with a low computational load. Finally, it is shown ihat the weighted Viterbi algorithm in combination with temporal constraints leads to a high recognition accuracy itt moderate SNR's without the need of an accurate noise model.
doi:10.1109/icassp.1998.675363 dblp:conf/icassp/YomaMJ98 fatcat:oekauuj76fcwnh3kekn227743q