Discriminative training for continuous speech recognition

Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully applied for automatic speech recognition. In this paper a discussion of the Minimum Classification Error and the Maximum Mutual Information objective is presented. An extended reestimation formula is used for the HMM parameter update for both objective functions. The discriminative training methods were utilized in speaker independent phoneme recognition experiments and improved the phoneme recognition rates for both discriminative training techniques.

[1]  L. R. Rabiner,et al.  An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[2]  Lalit R. Bahl,et al.  Maximum mutual information estimation of hidden Markov model parameters for speech recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Y.-L. Chow.  Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[4]  Dimitri Kanevsky,et al.  An inequality for rational functions with applications to some statistical estimation problems , 1991, IEEE Trans. Inf. Theory.

[5]  Renato De Mori,et al.  High performance connected digit recognition using maximum mutual information estimation , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[6]  Yves Normandin,et al.  Hidden Markov models, maximum mutual information estimation, and the speech recognition problem , 1992 .

[7]  Biing-Hwang Juang,et al.  Discriminative learning for minimum error classification [pattern recognition] , 1992, IEEE Trans. Signal Process..

[8]  Steve J. Young,et al.  MMI training for continuous phoneme recognition on the TIMIT database , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Günther Ruske,et al.  A new model-discriminant training algorithm for hybrid NN-HMM systems , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  G. Ruske,et al.  A hybrid RBF-HMM system for continuous speech recognition , 1995 .

[11]  Dimitri Kanevsky.  A generalization of the Baum algorithm to functions on non-linear manifolds , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.