Multilayer perceptrons for state-dependent weightings of HMM likelihoods

Speech Communication

Volumn 18, Issue 1, 1996, Pages 79-89

  Chung, Yong Joo ^a   Un, Chong Kwan ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

Multilayer perceptron; Speech recognition; Weighting of hidden Markov models

Indexed keywords

ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; NEURAL NETWORKS; SPEECH ANALYSIS; SPEECH PROCESSING; STATISTICAL METHODS;

HIDDEN MARKOV MODEL LIKELIHOODS; STATE DEPENDENT WEIGHTINGS; STATIC PATTERN CLASSIFICATION;

SPEECH RECOGNITION;

EID: 0029732695     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-6393(95)00038-0     Document Type: Article

References (21)

1. S. Amari (1967), "A theory of adaptive pattern classifiers", IEEE Trans. Electron. Comput., Vol. EC-16, No. 3, pp. 299-307.
2. L.R. Bahl, P.F. Brown, P.V. de Souza and R.L. Mercer (1986), "Maximum mutual information estimation of hidden Markov model parameters for speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Tokyo, Japan, April 1986, pp. 49-52.
3. L.R. Bahl, P.F. Brown, P.V. de Souza and R.L. Mercer (1988), "A new algorithm for the estimation of hidden Markov model parameters", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., New York, NY, April 1988. pp. 493-496.
4. L.E. Baum (1972), "An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov process", Inequalities, Vol. 3, pp. 1-8.
5. Y. Bengio, R.D. Mori, G. Flammia and R. Kompe (1992). "Global optimization of a neural network-hidden Markov model hybrid", IEEE Trans. Neural Networks, Vol. 3, pp. 252-258.
6. H.A. Bourlard and N. Morgan (1994), Connectionist Speech Recognition: A Hybrid Approach (Kluwer Academic Publishers, Norwell, MA.
7. H. Bourlard and C.J. Wellekens (1990), "Links between Markov models and multilayer perceptrons", IEEE Trans. Pattern Anal. Machine Intell., Vol. 12, pp. 1167-1178.
8. P.L. Cerf, W. Ma and D.V. Compernolle (1994). "Multilayer perceptrons as labelers for hidden Markov models", IEEE Trans. Speech Audio Process., Vol. 2, pp. 185-192.
9. P.C. Chang and B.H. Juang (1992), "Discriminative template training for dynamic programming speech recognition". Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., San Francisco, CA, March 1992, pp. 493-496.
10. W. Chou, B.H. Juang and C.H. Lee (1992), "Segmental GPD training of HMM based speech recognizer". Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., San Francisco, CA, March 1992, pp. 473-476.
11. W. Chou, C.H. Lee and B.H. Juang (1993). "Minimum error rate training based on N-best string models", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Minneapolis, Minnesota, April 1993, pp. 652-655.
12. Y.L. Chow (1990), "Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, April 1990, pp. 701-704.
13. Y.J. Chung and C.K. Un (1993), "Use of different numbers of mixtures in continuous density hidden Markov models", IEE Electronic Letters, Vol. 29, No. 9, pp. 824-825.
14. M.A. Franzini, M.J. Witbrock and K.F. Lee (1989), "A connectionist approach to continuous speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Glasgow, Scotland, May 1989, pp. 425-428.
15. B.H. Juang and S. Katagiri (1992), "Discriminative learning for minimum error classification", IEEE Trans. Signal Process., Vol. 40, pp. 3043-3054.
16. C.H. Lee and L.R. Rabiner (1989), "A frame-synchronous network search algorithm for connected word recognition", IEEE Trans. Acoust. Speech Signal Process., Vol. 37, pp. 1649-1658.
17. D. Lubensky, A. Asadi and M. Naik (1994), "Connected digit recognition using connectionist probability estimators and mixture-gaussian densities", Proc. Internat. Conf. Spoken Language Processing, Yokohama, Japan, September 1994, pp. 295-298.
18. N. Merhav and Y. Ephraim (1991), "Maximum likelihood hidden Markov modeling using a dominant sequence of states", IEEE Trans. Signal Process., Vol. 39, pp. 2111-2114.
19. K.Y. Su and C.H. Lee (1991). "Robustness and discrimination oriented speech recognition using weighted HMM and subspace projection approaches", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Toronto, Canada, May 1991, pp. 541-544.
20. A. Waibel and T. Hanazawa and G. Hinton and K. Shikano and K. Lang (1989), "Phoneme recognition using time-delay neural networks", IEEE Trans. Acoust. Speech Signal Processing, Vol. 37, pp. 328-339.
21. F. Wolferstetter and G. Ruske (1994), "Discriminative stateweighting in hidden Markov models", Proc. Internat. Conf. Spoken Language Process., Yokohama, Japan, September 1994, pp. 219-222.