Continuous Speech Recognition by Connectionist Statistical Methods

IEEE Transactions on Neural Networks

Volumn 4, Issue 6, 1993, Pages 893-909

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

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b Lernout & Hausnie Speech Products ^*  (Belgium)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING SYSTEMS; NEURAL NETWORKS; SPECTRUM ANALYSIS;

HIDDEN MARKOV MODELS; MULTILAYERS PERCEPTION; PHONETIC CONTEXT;

SPEECH RECOGNITION;

EID: 0027695851     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.286885     Document Type: Article

References (72)

1. S. I. Amari, “A theory of adaptive pattern classifiers,” IEEE Trans. Elec. Commun., vol. EC-16, pp. 279–307, 1967.
2. S. Austin, J. Makhoul, R. Schwartz, and G. Zavaliagos, “Continuous speech recognition using segmental neural networks,” in Proc. Fourth DARPA Workshop Speech and Natural Language, Feb. 1991.
3. L. R. Bahl, F. Jelinek, and R. Mercer, “A maximum likelihood approach to continuous speech recognition,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 179–190, Mar. 1983.
4. L. E. Baum, “An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov processes,” Inequalities, vol. 3, pp. 1–8, 1972.
5. L. Bottou, “Une approche theorique de l’apprentissage connexioniste: Applications a la reconnaissance de la parole,” Ph.D. dissertation, Univ. Paris Sud, Centre d'Orsay, 1991.
6. H. Bourlard and N. Morgan, “A continuous speech recognition system embedding MLP into HMM,” in Advances in Neural Information Processing Systems 2, D. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1990, pp. 186–193.
7. H. Bourlard and N. Morgan, “Merging multilayer perceptrons and hidden Markov models: Some experiments in continuous speech recognition,” in Neural Networks: Advances and Applications, E. Gelenbe, Ed. Amsterdam, The Netherlands: Elsevier, 1991.
8. H. Bourlard, N. Morgan, C. Wooters, and S. Renals, “CDNN: A context dependent neural network for continuous speech recognition,” in Proc. IEEE Inti. Conf Acoustics, Speech, Signal Processing, San Francisco, CA, 1992, pp. 349–352.
9. H. Bourlard and C. J. Wellekens, “Links between Markov models and multilayer perceptrons,” in Advances in Neural Information Processing 1, D. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989, pp. 502–510.
10. H. Bourlard and C. J. Wellekens, “Speech pattern discrimination and multilayer perceptrons,” Computer, Speech and Language, vol. 3, pp. 1–19, 1989.
11. H. Bourlard and C. J. Wellekens, “Links between Markov models and multilayer perceptrons,” IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 12, pp. 1167–1178, Dec. 1990.
12. J. Bridle, “Alpha-nets: A recurrent “neural” network architecture with a hidden Markov interpretation,” Speech Commun., vol. 9, no. 1, pp. 83–92, Feb. 1990.
13. P. Brown, “The acoustic-modeling problem in automatic speech recognition,” Ph.D. dissertation, Dep. Comput. Sci., CMU, 1987.
14. A. E. Bryson, Jr. and Y. C. Ho, Applied Optimal Control. Blaisdel, 1969.
15. M. Cohen, H. Franco, N. Morgan, D. Rumelhart, and V. Abrash, “Context-dependent multiple distribution phonetic modeling,” in Advances in Neural Information Processing Systems 5, D. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, to be published.
16. A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood estimation from incomplete data via the EM algorithm,” J. Roy. Statist. Soc., vol. 39(B), pp. 1–38, 1977.
17. J. L. Elman, “Finding structure in time,” CRL Tech., UCSD, Tech. Rep., 1988.
18. M. A. Franzini, K. F. Lee, and A. Waibel, “Connectionist Viterbi training: A new hybrid method for continuous speech recognition,” in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, Albuquerque, NM, Apr. 1990, pp. 425-428.
19. A. Gevins and N. Morgan, “Ignorance-based systems,” in IEEE Proc. 1985 Int. Conf.ASSP, vol. 3, San Diego, CA, 1985, pp. 39A5.1-39A5.4.
20. H. Gish, “A probabilistic approach to the understanding and training of neural network classifiers,” in IEEE Proc. 1990 Int. Conf. ASSP, vol. 3, Albuquerque, NM, Apr. 1990, pp. 1361–1364.
21. P. Haffner, M. Franzini, and A. Waibel, “Integrating time alignment and neural networks for high performance continuous speech recognition,” in IEEE Proc. 1991 Int. Conf. ASSP, vol. 1, Toronto, Canada, 1991, pp. 105–108.
22. H. Hermansky, “Perceptual linear predictive (PLP) analysis of speech,” J. Acoust. Soc. Amer., vol. 87, no. 4, Apr. 1990.
23. G. E. Hinton, “Connectionist learning procedures,” Carnegie Mellon Univ., Tech. Rep. CMU-CS-87-115, 1987.
24. F. Jelinek, “Continuous speech recognition by statistical methods,” Proc. IEEE, vol. 64, no. 4, pp. 532–555, 1976.
25. M. L. Jordan, “Serial order: A parallel distributed processing approach,” Tech. Rep. 8604, UCSD, 1986.
26. Y. Konig and N. Morgan, “GDNN: A gender-dependent neural network for continuous speech recognition,” in Proc. IJCNN ' 92, pp. 332–337.
27. G. Kuhn and N. Herzberg, “Variations on training of recurrent networks,” in Proc. 24th Conf. Information Sciences and Systems, Princeton, NJ, Mar. 1990.
28. T. K. Landauer, C. A. Kamm, and S. Singhal, “Teaching a minimally structured back propagation network to recognize speech,” in Proc. Ninth Annu. Conf. Cognitive Science Soc., 1987, pp. 531–536.
29. K. F. Lee, Automatic Speech Recognition: The Development of the SPHINX System. Boston, MA: Kluwer, 1989.
30. K. F. Lee, “Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 38, no. 4, pp. 599–609, 1990.
31. E. Levin, “Speech recognition using hidden control neural network architecture,” in IEEE Proc. 1990 Int. Conf. ASSP, Albuquerque, NM, 1990.
32. S. E. Levinson, L. R. Rabiner, and M. M. Sondhi, “An introduction to the theory of application of probabilistic functions on a Markov process to automatic speech recognition,” Bell Syst. Tech. J., vol. 62, no. 4, Apr. 1983.
33. R. P. Lippmann and B. Gold, “Neural classifiers useful for speech recognition,” in Proc. First Int. Conf. Neural Networks, San Diego, CA, 1987, pp. IV-417.
34. R. P. Lippmann, “An introduction to computing with neural nets,” IEEE ASSP Mag., vol. 3, pp. 4–22, 1987.
35. N. Morgan, C. Wooters, H. Bourlard, and M. Cohen, “Continuous speech recognition on the resource management database using connectionist probability estimation,” in Proc. Int. Conf Spoken Language Processing, Kobe, Japan, Nov. 1990, pp. 31.1.1-31.1.4.
36. N. Morgan and H. Bourlard, “Continuous speech recognition using multilayer perceptrons with hidden Markov models,” in IEEE Proc. 1990 Int. Conf. ASSP, Albuquerque, NM, Apr. 1990, pp. 413-416.
37. N. Morgan, J. Beck, P. Kohn, J. Bilmes, E. Allman, and J. Beer, “The RAP: A ring array processor for layered network calculations,” in Proc. Int. Conf. Application Specific Array Processors, IEEE Comput. Soc. Press, Princeton, NJ, 1990, pp. 296–308.
38. N. Morgan, H. Hermansky, H. Bourlard, P. Kohn, and C. Wooters, “Continuous speech recognition using PLP analysis with multilayer perceptrons,” in IEEE Proc. 1991 Int. Conf ASSP, Toronto, Canada, May 1991, pp. 49–52.
39. H. Murveit and R. W. Brodersen, “An integrated-circuit-based speech recognition system,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 34, no. 6, pp. 1465–1472, 1986.
40. H. Murveit and M. Weintraub, “1000-word speaker-independent continuous-speech recognition using hidden Markov models,” in IEEE Proc. 1988 Int. Conf. ASSP, vol. 1, New York, 1988, pp. 115–118.
41. H. Murveit, M. Cohen, P. Price, G. Baldwin, and M. Weintraub, “SRI’s DECIPHER system,” in Proc. DARPA Speech and Natural Language Workshop, Feb. 1989.
42. A. Nadas, D. Nahamoo, and M. A. Picheny, “On a model-robust training method for speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 35, no. 9, pp. 1432–1436, 1988.
43. I. Newton, Philosophiae Naturalis Principae Mathematica. London, England: Royal Society Press, 1687.
44. H. Ney, “The use of one-stage dynamic programming algorithm for connected word recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-32, pp. 263–272, 1984.
45. H. Ney, “Speech recognition in a neural network framework: Discriminative training of Gaussian models and mixture densities as radial basis functions,” in IEEE Proc. 1991 Int. Conf. ASSP, vol. 1, Toronto, Canada, 1991, pp. 573–576.
46. H. Ney and A. Noll, “Phoneme modeling using continuous mixture densities,” in IEEE Proc. 1990 Int. Conf. ASSP, vol. 1, New York, 1988, pp. 437–440.
47. L. Niles, H. Silverman, G. Tajchman, and M. Bush, “How limited training data can allow a neural network classifier to outperform an ‘optimal’ statistical classifier,” in IEEE Proc. 1989 Int. Conf. ASSP, vol. 1, Glasgow, Scotland, 1989, pp. 17–20.
48. L. T. Niles and H. F. Silverman, “Combining hidden Markov models and neural network classifiers,” in IEEE Proc. 1990 Int. Conf ASSP, Albuquerque, NM, Apr. 1990, pp. 417–420.
49. D. Parker, “Learning logic,” Office Technol. Licensing, Stanford Univ., Stanford, CA, Invention Rep. S81-64, File 1, 1982.
50. D. Parker, “Learning logic,” Center Computational Res. Econ. Management Sci., M.I.T., Tech. Rep. TR-47, 1985.
51. D. B. Paul, “The Lincoln robust continuous speech recognizer,” in IEEE Proc. 1989 Int. Conf. ASSP, Glasgow, Scotland, May 1989.
52. D. B. Paul, “The Lincoln tied-mixture HMM continuous speech recognizer,” in IEEE Proc. 1991 Int. Conf. ASSP, Toronto, Canada, 1991, pp. 329–-332.
53. D. B. Paul, J. K. Baker, and J. M. Baker, “On the interaction between true source, training, and testing language models,” in IEEE Proc. 1991 Int. Conf ASSP, Toronto, Canada, 1991, pp. 569–572.
54. S. M. Peeling and R. K. Moore, “Isolated digit recognition experiments using the multilayer perceptron,” Speech Commun., vol. 7, pp. 403–409, 1988.
55. T. Poggio and F. Girosi, “Networks for approximation and learning,” Proc. IEEE, vol. 78, no. 9, pp. 1481–1497, 1989.
56. S. Renals, “Speech and neural network dynamics,” Ph.D. dissertation, Dep. Phys., Univ. Edinburgh, 1990.
57. S. Renals, N. Morgan, H. Bourlard, H. Franco, and M. Cohen, “Connectionist optimization of tied mixture hidden Markov models,” in Advances in Neural Information Processing Systems 4, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1992.
58. T. Robinson and F. Fallside, “Phoneme recognition from the TIMIT database using recurrent error propagation networks,” Dep. Eng., Cambridge Univ., Tech. Rep. CUED/F-INFENG/TR.42, Mar. 1990.
59. T. Robinson and F. Fallside, “A recurrent error propagation network speech recognition system,” Comput., Speech, Language, 1991.
60. F. Rosenblatt, “On the convergence of reinforcement procedures in simple perceptrons,” Cornell Aeronautical Lab., Buffalo, NY, Rep. VG-1196-G-4, 1960.
61. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing. Exploration of the Microstructure of Cognition, vol. 1: Foundations, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986.
62. R. Schwartz, Y. Chow, O. Kimball, Roucos, M. Krasner, and J. Makhoul, “Context-dependent modeling for acoustic-phonetic recognition of continuous speech,” in IEEE Proc. 1985 Int. Conf. ASSP, Tampa, FL, Apr. 1985.
63. D. F. Specht, “Probabilistic neural networks,” Neural Networks, vol. 3, no. 1, pp. 109–118, 1990.
64. A. Sitoelzle, S. Narayanaswamy, P. Schrupp, B. Richards, R. Yu, J. Rabaey, and R. Brodersen, “A flexible VLSI 60,000 word real-time continuous speech recognition system,” in VLSI Signal Processing IV, H. S. Moscovitz, K. Yao, and R. Jain, Eds. New York: IEEE Press, 1991.
65. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. Lang, “Phoneme recognition using time-delay neural networks,” in IEEE Proc. 1988 Int. Conf ASSP, New York, 1988.
66. R. L. Watrous and L. Shastri, “Learning phonetic features using connectionist networks: An experiment in speech recognition,” in Proc. First Int. Conf. Neural Networks, San Diego, CA, 1987, pp. IV-381-388.
67. R. L. Watrous, B. Ladendorf, and G. Kuhn, “Complete gradient optimization of a recurrent network applied to ib/,/d/,/g/ discrimination,” J. Acoust. Soc. Amer., vol. 87, no. 3, pp. 1302–1309, Mar. 1990.
68. P. J. Werbos, “Beyond regression: New tools for prediction and analysis in the behavioral sciences,” Ph.D. dissertation, Dep. Appl. Math., Harvard Univ., 1974.
69. B. Widrow and M. E. Hoff, “Adaptive switching circuits,” Stanford Electron. Labs., Stanford, CA, Tech. Rep. 1553-1, 1960.
70. X. L. Aubert, “Supervised phonetic segmentation with with applications to speech recognition,” Proc. European Con & Speech Technology, Edinburgh, (GB), vol 2, pp. 161–164, 1987.
71. M. D. Richard and R. P. Lippman, “Neural network classifiers estimate Bayesian a posteriori probabilities,” Neural Computation, vol. 3, no. 4, pp. 461–483, 1991.
72. H. Bourlard and N. Morgan, Connectionist Speech Recognition: AHybrid Approach. Kluwer Academic Publishers, 1994.