A Hybrid Segmental Neural Net/Hidden Markov Model System for Continuous Speech Recognition

IEEE Transactions on Speech and Audio Processing

Volumn 2, Issue 1, 1994, Pages 151-160

  Zavaliagkos, G ^a   Zhao, Y ^b   Schwartz, R ^b   Makhoul, J ^b  

^a NORTHEASTERN UNIVERSITY   (United States)

^b BBN TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

NEURAL NETWORKS;

CONNECTIONIST COMPONENT; CONTINUOUS SPEECH RECOGNITION; DARPA RESOURCE MANAGEMENT (RM) CORPUS; HIDDEN MARKOV MODELS (HMM); SEGMENTAL NEURAL NET (SNN) MODELS; SPEAKER-INDEPENDENT EXPERIMENTS;

SPEECH RECOGNITION;

EID: 0028288775     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.260358     Document Type: Letter

References (33)

1. L.R. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257–285, Feb. 1989.
2. X. Huang, Y. Ariki, and M. Jack, Hidden Markov Models for Speech Recognition. Edinburgh, U.K.: Edinburgh Univ. Press, 1990.
3. K.F. Lee, Automatic Speech Recognition: The Development of the SPHINX System. Norwell, MA: Kluwer, 1989.
4. S. Austin et al., “Toward a realtime spoken language system using commercial hardware,” in Proc. DARPA Speech, Natural Language Workshop (Hidden Valley, PA), June 1990.
5. S. Katagiri and C.H. Lee, “A new HMM/LVQ hybrid algorithm for speech recognition,” in Proc. GLOBECOM′90.
6. K. Fukuzawa, Y. Komori, H. Sawai, and M. Sugiyama, “A segment-based speaker adaptation neural network applied to continuous speech recognition,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (San Francisco, CA), Mar. 1992, pp. 433–446.
7. H.C. Leung, I.L. Hetherington, and V. Zue,” Speech recognition using stochastic segment neural networks,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (San Francisco, CA), Mar. 1992, pp. 613–616.
8. M. Ostendorf and S. Roukos, “A stochastic segment model for phoneme-based continuous speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 1857–1869, Dec. 1989.
9. M. Bates et al., “The BBN/HARC spoken language understanding system,” IEEE Int. Conf. Acoust., Speech, Signal Processing (Minneapolis, MN), Apr. 1993.
10. G. Cybenko, “Approximations by superpositions of a sigmoidal function,” in Mathematics of Control, Signals and Systems. New York: Springer-Verlag, 1989
11. T. Poggio and F. Girasi, “Networks for approximation and learning,” Proc. IEEE, vol. 78, pp. 1481–1497, Sept. 1990.
12. H. White, “Learning in artificial neural networks: A statistical perspective,” Neural Computation, pp. 425–464, 1989.
13. J. Patterson and B. Womack, “An adaptive pattern classification system,” IEEE Trans. Syst., Sci., Cybern., pp. 62–67, Aug. 1966.
14. A. Barron, “Statistical properties of artificial neural networks,” in Proc. IEEE Conf. Decision, Control (Tampa, FL), pp. 280–285, 1989.
15. H. Gish, “A probabilistic approach to the understanding and training of neural network classifiers,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Apr. 1990.
16. S. Renals, N. Morgan, M. Cohen, and H. Francom “Connectionist probability estimation in the DECIPHER system,” IEEE Int. Conf. Acoustics, Speech, Signal Processing (San Francisco, CA), Apr. 1992, pp. 601–604.
17. T. Robinson, “Recurrent nets for phone probability estimation,” in Proc. DARPA Workshop Continuous Speech Recognition, unpublished.
18. M. Ostendorf et al., “Integration of Diverse Recognition Methodologies Through Reevaluation of N-est sentence hypotheses,” in Proc. DARPA Speech, Natural Language Workshop (Pacific Grove, CA), Feb. 1991.
19. R. Schwartz et al., “New uses for the N-best sentence hypotheses within the BYBLOS speech recognition system,” IEEE Int. Conf. Acoust., Speech, Signal Processing (San Francisco, CA), Mar. 1992, pp. 1–4.
20. R. Schwartz and Y.L. Chow, “The N-Best algorithm: an efficient and exact procedure for finding the N most likely sentence hypotheses,” IEEE Int. Conf. Acoust., Speech. Signal Processing (Albuquerque, NM), Apr. 1990, pp. 81–84.
21. R. Schwartz and S. Austin, “A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses,” IEEE Int. Conf. Acoust., Speech, Signal Processing (Toronto, Ont.), May 1991, pp. 701–704.
22. P. Price, W. Fischer, J. Bernstein, and D. Pallett, “The DARPA 1000-word resource management database for continuous speech recognition,” IEEE Int. Conf. Acoust., Speech, Signal Processing (New York), Apr. 1988, pp. 651–654.
23. A. El-Jaroudi and J. Makhoul, “A new error criterion for posterior probability estimation with neural nets,” Int. Joint Conf. Neural Networks (San Diego, CA), vol. DJ, June 1990, pp. 185–192.
24. D. Luenberger, Linear and Nonlinear Programming. Reading, MA: Addison-Wesley, 1984.
25. R. Schwartz, Y.L. Chow, S. Roucos, M. Krasner, and J. Makhoul, “Improved hidden Markov modeling of phonemes for continuous speech recognition,” IEEE Int. Conf. Acoust., Speech, Signal Processing (San Diego, CA), Mar. 1984, pp. 35.6.1–35.6.4.
26. A.N. Tikhonov and V.Y. Arsenin. Solutions to Ill-Posed Problems. Washington, DC: W.H. Winston, 1977.
27. J. Moody, “The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems,” Advances in Neural Information Processing Syst. 4, J.E. Moody, S.J. Hanson, and R.P. Lippman, Eds. San Francisco, CA: Morgan Kaufmann, 1991.
28. G. Wahba, “Spline models for observational data,” CBMS-NSF Regional Conf. Series Applied Mathematics, 1990.
29. F. Girosi and T. Poggio, “Networks and the best approximation property,” Biological Cybernetics, vol. 63, pp. 169–176, 1990.
30. M. Stinchcombe and H. White, “Universal approximation using feedforward networks with nonsigmoidal hidden layer activation functions,” in Proc. Int. Joint Conf. Neural Networks (Washington, DC), June 1989, pp. I-607-I-611.
31. R. Schwartz et al., “Robust smoothing methods for discrete hidden Markov models,” in Proc. IEEE Int. Conf. Acoust, Speech, Signal Processing (San Diego, CA), Mar. 1984, pp. 35.6.1–35.6.4.
32. F. Kubala et al., “BYBLOS speech recognition benchmark results,” in Proc. DARPA Speech, Natural Language Workshop (Pacific Grove, CA), Feb. 1991.
33. D.S. Pallet, J.G. Fiscus, and J.S. Garofolo, “Resource management corpus: Sept. 1992 test set benchmark test results,” ARPA Continuous Speech Recognition Workshop (Stanford University, CA), Sept. 1992, pp. 1–18.