REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities - Application to Transition-Based Connectionist Speech Recognition

NIPS 1995: Proceedings of the 8th International Conference on Neural Information Processing Systems

Volumn , Issue , 1995, Pages 388-394

  Konig, Yochai ^a   Bourlard, Hervé ^a,b   Morgan, Nelson ^a  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b Univ de l'Etat Mons   (Belgium)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; NEURAL NETWORKS;

A-POSTERIORI PROBABILITIES; BASELINE SYSTEMS; ERROR RATE; HIDDEN-MARKOV MODELS; NEW APPROACHES; POSTERIOR PROBABILITY; RECURSIVE ALGORITHMS; RECURSIVE ESTIMATION; STATISTIC MODELING;

SPEECH RECOGNITION;

EID: 84910103509     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. BENGIO, Y., & P. FRASCONI. 1995. An input output HMM architecture. In Advances in Neural Information Processing Systems, ed. by G. Tesauro, D, Touretzky, & T. Leen, volume 7. Cambridge: MIT press.
2. BENGIO, Y., R. DE MORI, G. FLAMMIA, & R. KOMPE. 1992. Global optimization of a neural network-hid den Markov model hybrid. IEEE trans, on Neural Networks 3.252-258.
3. BOURLARD, H., Y. KONIG, & N. MORGAN. 1994. REMAP: Recursive estimation and maximization of a posteriori probabilities, application to transition-based connectionist speech recognition. Technical Report TR-94-064, International Computer Science Institute, Berkeley, CA.
4. BOURLARD, H., Y. KONIG, & N. MORGAN. 1994. Connectionist Speech Recognition - A Hybrid Approach. Kluwer Academic Publishers.
5. BOURLARD, H., Y. KONIG, & C. J. WELLEKENS, 1989. Links between Markov models and multilayer perceptrons. In Advances in Neural Information Processing Systems 1, ed. by D. J. Touretzky, 502-510, San Mateo. Morgan Kaufmann.
6. COLE, R. A., M. FANTY, & T. LANDER. 1994. Telephone speech corpus development at CSLU. In Proceedings Int'l Conference on Spoken Language Processing, Yokohama, Japan.
7. DEMPSTER, A. P., N. M. LAIRD, & D. B. RUBIN. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B 34.1-38.
8. GLASS, J. R., 1988. Finding Acoustic Regularities in Speech Applications to Phonetic Recognition. M. I. T dissertation.
9. KATAGIRI, S., C. H. LEE, & JUANG B. H. 1991. New discriminative training algorithms based on the generalized probabilistic decent method. In Proc. of the IEEE Workshop on Neural Netwroks for Signal Processing, ed. by B. H. Juang, S. Y. Kung, & CA. Kamm, 299-308.
10. KONIG, Y., & N. MORGAN, 1994. Modeling dynamics in connectionist speech recognition - the time index model. In Proceedings Int l Conference on Spoken Language Processing, 1523-1526, Yokohama, Japan.
11. LIPORACE, L. A. 1982. Maximum likelihood estimation for multivariate observations of markov sources. IEEE Trans. on Information Theory IT-28.729-734.
12. MORGAN, N., H. BOURLARD, S. GREENBERG, & H. HERMANSKY. 1994. Stochastic perceptual auditory-event-based models for speech recognition. In Proceedings Int'l Conference on Spoken Language Processing, 1943-1946, Yokohama, Japan.