Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition

Proceedings of the IEEE

Volumn 88, Issue 8, 2000, Pages 1201-1223

  Wu, Chou ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

Combined siring model; Discriminant function; Hidden markov model; Minimum recognition error rate; Speech recognition

Indexed keywords

EID: 0000767590     PISSN: 00189219     EISSN: None     Source Type: Journal    
DOI: 10.1109/5.880080     Document Type: Article

References (113)

1. S.-I. Amari, "A theory of adaptive pattern classifiers," IEEE Trans. Electron. Compta., vol. EC-16, no. 3, pp. 299-307, 1967.
2. _, "Learning patterns and pattern sequences by self-organizing nets of threshold elements," IEEE Trans. Comput., vol. C-12, pp. 1197-1206, Nov. 1972.
3. L. R. Bahl, P. F. Brown, P. V. deSouza, and R. L. Mercer, "Maximum mutual information estimation of HMM parameters for speech recognition," in Proc. ICASSP-86, 1986, pp. 49-52.
4. _, "Estimating hidden Markov model parameters so as to maximize speech recognition accuracy," IEEE Trans. Speech Audio Processing, vol. 1, pp. 77-83, Jan. 1993.
5. L. R. Bahl, F. Jelinek, and R. L. Mercer, "A maximum likelihood approach to continuous speech recognition," IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 79-190, Mar. 1983.
6. L. E. Baum, T. Petrie, G. Soules, and N. Weiss. "A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains," Ann. Math. Statist., vol. 41, pp. 164-171, 1970.
7. L. E. Baum, "An inequality and associated maximization techniques in statistical estimation for probabilistic fimciioas of Markov process," Inequalities, vol. 3, pp. 1-8, 1972.
8. L. E. Baum and J. A. Eagon, "An inequality with applications to statistical predication fer functions of Markov process and to model of ecology." Bull. Amer. Mash Soc., vol. 73, pp. 360-363, 1967.
9. L. E. Baum and G. Sell, "Growth transformations for functions on manifolds," Pacific J. Math., vol. 27, no. 2, pp. 211-227, 1968.
10. X. Bickel and X. Doksum, Mathematical Statistics. Englewood Cliffs, NJ: Prentice-Hail, 1977.
11. A. Benveniste, M. Metivier, and P. Priouet, Adaptive Algorithms and Stochastic Approximations, Berlin, Germany: Springer-Verlag.
12. P. Beyerlein, "Discriminative model combination," in Proc. 1997 Workshop Automatic Speech Recognition and Understanding Proceedings, Dec. 1997, pp. 238-245.
13. A. Biem, S. Katagiri, and B.-H. Juang, "Pattern recognition using discriminative feature extraction," IEEE Trans. Signal Processing, vol. 45, pp. 500-504, Feb. 1997.
14. J. R. Blum, "Multidimensional stochastic approximation methods," Ann. Math. Stat., vol. 25. pp. 737-744, 1954.
15. P.-C. Chang and B.-H. Juang, "Discriminative template training for dynamic programming speech recognition," in Proc. ICASSP92, vol. 1, 1992, pp. 493-496.
16. _, "Discriminative training for dynamic programming based speech recognizers," IEEE Trans. Speech Audio Processing, vol. 1, pp. 135-143, Apr. 1993.
17. W. Chou, C.-H. Lee, and B. H. Juang, "Segmental GPD training of an hidden Markov model based speech recognizer," in Proc. IEEE ICASSP-92, Apr. 1992, pp. 473-476.
18. _, "Minimum error rate training based on N-best string models," in Proc. IEEE ICASSP-93, Apr. 1993, pp. 11-652-655.
19. _, "Minimum error rate training of inter-word context dependent acoustic model units in speech recognition," in Proc. ICSEP-94, Yokohama, Japan, 1994, pp. 439-442.
20. W. Chou, B-H. Juang, and C.-H. Lee, "Minimum error rate training of combined string models." U.S. Patent 5 606 644.
21. W. Chou, C.-H. Lee, and B.-H. Juang, "Speech recognition based on combined string models." in Proc. DARPA ANN Tech. Program CSR Mtg., Sept. 1992, pp. 65-69.
22. W. Chou, C.-H. Lee, B.-H. Juang, and F. K. Soong, "A minimum error rate pattern recognition approach to speech recognition," Int. J. Pattern Recog. Artif. Intell., vol. 8, no. 1, pp. 5-31, 1994.
23. W. Chou and B.-H. Juang, "Adaptive discriminative learning in pattern recognition," Tech. Rep., AT&T Bell Laboratories. 1992.
24. T. Cover and J. Thomas, Elements of Information Theory. New York: Wiley, 1991.
25. S. M. Chu and Y. Zhao, "Robust speech recognition using discriminative stream weighting and parameter interpolation," in Proc. IEEE ICSLP'98, Nov. 1998, pp. 690-694.
26. H. Do-Tu and M. Installe, "Learning algorithms for nonparametric solution to minimum error classification problem," IEEE Trans. Cornput., vol. C-27, pp. 648-659, July 1978.
27. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Roy. Soc. B., vol. 39, pp. 1-38, 1977.
28. J. L. Doob, Stochastic Process. New York: Wiley, 1953.
29. R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis. New York: Wiley, 1973.
30. Y. Ephraim and L. Rabiner, "On the relation between modeling approaches for speech recognition," IEEE Trans. Inform. Theory, vol. 36, pp. 372-380, Mar. 1990.
31. Y. Ephraim, A. Dembo, and L. Rabiner, "A minimum discrimination information approach for hidden Markov modeling," IEEE Trans. Inform. Theory, vol. 35. pp. 1001-1013, Mar. 1989.
32. J. Fiscus, "A post-processing system to yield reduced word error rate.'' in Proc. 1997 IEEE Workshop Automatic Speech Recognition and Understanding, 1997, pp. 347-354.
33. M. B. Gandhi and J. Jacob, "Natural number recognition using MCE trained inter-word context dependent acoustic models," in Proc. IEEE ICASSP'98, 1998, pp. 457-461.
34. C. M. del Alamo et al., "Discriminative training of GMM for speaker identification," in Proc. IEEE ICASSP'96, 1996, pp. 89-93.
35. P. S. Gopalakrishnan et al., "An inequality for rational functions with applications to some statistical estimation problems." IEEE Trans. inform. Theory, vol. 37, pp. 107-113, Jan. 1991.
36. _, "Decoder selection based on cross-entropies," in Proc. IEEE ICASSP'88, 1988, pp. 20-23.
37. S. Herman and R. Sukkar, "Joint MCE estimation of VQ and HMM parameters for Gaussian mixture selection," in Proc. IEEE ICASSP'98, 1998, pp. 485-488.
38. Q. Huo and C. Chan, "The gradient projection method for the training of hidden Markov models," Speech Commun., vol. 13, pp. 307-313, 1993.
39. X. Huang, M. Belin, F. Alleva, and M. Hwang, "Unified stochastic engine (USE) for speech recognition," in Proc. IEEE ICASSP-93, Apr. 1992, pp. 636-639.
40. F. Jelinek, "The development of an experimental discrete dictation recognizer," Proc. IEEE, vol. 73, pp. 1616-1624, Nov. 1985.
41. _, "Continuous speech recognition by statistical methods," Proc. IEEE, vol. 64, pp. 532-556, Apr. 1976.
42. F. Jelinek, R. L. Mercer, and S. Roukos, "Principles of lexical language modeling for speech recognition," in Advances in Speech Signal Processing, S. Furui and M. M. Sondhi, Eds. New York: Marcel Dekker, 1991, pp. 651-699.
43. F. Jelinek, Statistical Methods for Speech Recognition. Cambridge, MA: MIT Press, 1997.
44. B.-H. Juang, L. R. Rabiner, and J. G. Wilpon, "On the use of bandpass littering in speech recognition," IEEE Trans. Acoust., Speech. Signal Processing vol. ASSP-35, pp. 947-954, July 1987.
45. B.-H. Juang and L. R. Rabiner, "Hidden Markov models for speech recognition," Technometrics, vol. 33, pp. 251-272, Aug. 1991.
46. B.-H. Juang, L. R. Rabiner, and J. G. Wilpon, "On the use of bandpass littering in speech recognition," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-35. pp. 947-954, July 1987.
47. B.-H. Juang, S. S. Levinson, and M. M. Sondhi, "Maximum likelihood estimation for multivariaie mixture observations of Markov chains," IEEE Trans. Inform. Theory, vol. IT-32, pp. 307-309, Feb. 1986.
48. B.-H. Juang and L. Rabiner, "The segmental K-means algorithm for estimating parameters of hidden Markov models," IEEE Trans. Acoust., Speech, Signal Processing, vol. 38, pp. 1639-1641, Sept. 1990.
49. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error training," IEEE Trans. Acoust., Speech, Signal Processing, vol. 40, pp. 3043-3054, Dec. 1992.
50. B.-H. Juang, W. Chou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Trans. Speech Audio Processing, vol. 5, May 1997.
51. D. Kavensky, "Generalization of Baum algorithm to functions on nonlinear manifolds," in Proc. ICASSP'95, vol. 1, Detroit, MI, 1995, pp. 473-476.
52. M. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer," IEEE Trans. Acoust., Speech, Signal Processing vol. ASSP-35, pp. 400-401, Mar. 1987.
53. T. Kawahara, C.-H. Lee, and B.-H. Juang, "Key-phrase detection and verification for flexible speech understanding," in 4th Int. Conf. ICSLP'96, vol. 2, 1996, pp. 861-864.
54. _, "Combining key-phrase detection and subworil-based verification for flexible speech understanding," in Proc. ICASSP'97, 1997, pp. 1159-1163.
55. T. Komori and S. Katagiri, "Application of a generalized probabilistic descent method of dynamic time vvarping-based speech recognition," in Proc. IEEE ICASSP-92, 1992, pp. 497-500.
56. S. Katagiri, C.-H. Lee, B.-H. Juang, and T. Komori, "New discriminative training algorithms based on a generalized probabilistic descent method," in Proc. IEEE SP Workshop Neural Networks for Signal Processing, Princeton, NJ, 1991.
57. S. Katagiri, B.-H. Juang, and A. Bieni, "Discriminative feature extraction," in Artificial Neural Nehvorks fur Speech and Vision, R. Mammone, Ed. London, U.K.: Chapman and Hall, 1994.
58. S. Katagiri, B.-H. Juang, and C.-H. Lee, "Pauern recognition using a family of design algorithms based upon the generalized probability descent method," Proc. IEEE, vol. 86, pp. 2345-2373. Nov. 1998.
59. M.-W, Koo, C.-H. Lee, and B.-H. Juang, "Speech recognition and utterance verification based on a generalized confidence score," IEEE Trans. Speech Audio Processing, to be published.
60. _, "A new decoder based on a generalized confidence score," presented at the Proc. ICASSP'98, May 1998.
61. F. Kormanzskiy and B.-H. Juang. "Discriminative adaptation for speaker verification," in Proc. IEEE ICSLP'96, 1996. pp. 1744-1747.
62. K.-K Lee, The Development of the SPHINX System. Norwell, MA: Kluwer, 1989.
63. A. Ljolje, Y. Ephraim, and L. Rabiner, "Estimating hidden Markov model parameters by minimizing empirical error rate," in Proc. ICASSP'90, 1990. pp. 709-712.
64. E. L. Lehmann, Testing Statistical Hypotheses. New York: Wiley, 1959.
65. E. Lleida and R. Rose, "Efficient decoding and training procedures for utterance verification in continuous speech recognition," in Proc. ICASSP'96, May 1996.
66. C.-H. Lee, B.-H. Juang, W. Chou, and J. J. Molina-Perez, "A study on task-independent subword selection and modeling for speech recognition," in Proc. ICSLP96, Philadelphia, PA. 1996, pp. 1816-1319.
67. C.-H. Lee, E. Giachin, L. R. Rabiner, R. Pieraccini, and A. E. Rosenberg, "Improved acoustic modeling for speaker independent large vocabulary continuous speech recognition," Comput. Speech Lang., vol. 4, no. 2, pp. 103-127, 1992.
68. C.-H. Lee, F. K. Soong, and F. K. Paliwal, Eds., Automatic Speech and Speaker Recognition, Norwell, MA: Kluwer, 1996.
69. Q. Li, B.-H. Juang, Q. Zhou, and C.-H. Lee, "Verbal information verification," in Proc. EuroSpeech'97, Sept. 1997.
70. C.-H. Lee, "A tutorial on speaker and speech verification," in Proc. NORSIG'98, June 1998, pp. 9-16.
71. Q. Li and B.-H. Juang, "Speaker verification using verbal information verification for automatic enrollment," presented at the Proc. ICASSP'98. May 1998.
72. C.-S. Liu, H.-C. Wang, and C.-H. Lee, "Speaker verification using normalized log-likelihood score," IEEE Trans. Speech Audio Processing, vol. 4, pp. 56-60, Jan. 1996.
73. C.-S. Liu, C.-H. Lee, W. Chou, B.-H. Juang, and A. Rosenberg, "A study on minimum error discriminative training for speaker recognition," J. Acoust. Soc. Amer., vol. 97, no. 1, pp. 637-648, 1995.
74. M. G. Rahim and C.-H. Lee, "Simultaneous ANN feature and HMM recognizer design using string-based minimum classification training of HMMs," in Proc. ICSLP'96, 1996, pp. 1824-1827.
75. M. G. Rahim, C.-H. Lee, B.-H. Juang, and W. Chou, "Discriminative utterance verification using minimum string verification error (MSVE) training," in Proc. ICASSP'96, 1996, pp. 3485-3588.
76. M. G. Rahim and C.-H. Lee, "String based minimum verification error (SB-MVE) training for flexible speech recognition," Comput. Speech Lang., 1997.
77. M. G. Rahim, C.-H. Lee, and B.-H. Juang, "Discriminative utterance verification for connected digit recognition," IEEE Trans. Speech Audio Processing, vol. 5, May 1997.
78. P. McMahon, N. Harte, S. Vaseghi, and P. McCourt, "Discriminative spectral-temporal multi-resolution features for speech recognition," in Proc. IEEE ICASSP'99, 1999, pp. 1649-1653.
79. E. McDemoi and S. Katagiri, "Prototype-based MCE/GPD training for various speech units." Comput. Speech Lang., vol. 8, pp. 351-368, 1994.
80. _, "String-level MCE for continuous phoneme recognition," in Proc. EuroSpeech'97, vol. 1, 1997, pp. 123-126.
81. J. M. Mendel and K. S. Fu, Adaptive, Leaning and Pattern Recognition. Xew York: Academic, 1970.
82. A. Nadas, D. Nahamoo, and M. A. Picheny, "On a model-robust training method for speech recognition," IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, pp. 1432-1436, Sept. 1988.
83. Y. Normandin et al., "High performance connected digit recognition using maximum mutual information estimation," IEEE Trans. Speech Audio Processing, vol. 2. pp. 229-311, Apr. 1994.
84. K. A. Papineni, "Discriminative training via linear programming," in Proc. ICASSP'99.
85. K. K. Paliwal, M. Bacchiani, and Y. Sagisaka, "Minimum classification error training algorithm for feature extraction and pattern classifier in speech recognition," in Proc. EuroSpeech'95. pp. 541-554.
86. D. Pollard, Convergence of Stochastic Process. Berlin, Germany: Springer-Verlag, 1984.
87. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, pp. 257-286, Feb. 1989.
88. L. R. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition. Engiewood Cliffs, NJ: Prentice-Hall, 1993.
89. C. Rathinavelu and L. Deng, "Use of generalized dynamic feature parameters for speech recognition: Maximum likelihood and minimum classification error approaches," in Proc. IEEE ICASSP'95, 1995, pp. 373-376.
90. _, "The trend HMM with discriminative training for phonetic classification," presented at the Proc. IEEE ICSLP'96.
91. _, "HMM based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features" presented at the Proc. IEEE ICASSP'96, 1996, pp. 9-13.
92. W. Reichl and G. Ruske, "Discriminative training for continuous speech recognition," in Proc. 1995 EuroSpeech'95, vol. 1, Madrid, Spain, Sept. 1995, pp. 537-540.
93. W. Reichl, "Language model adaptation using minimum discrimination information." in Proc. EuroSpeech'99, Budapest, Hungary, 1999, pp. 1791-1794.
94. W. Reichl and S. Ortmanns, "Integrated natural language call routing," in Proc. ESC'A Workshop Interactive Dialogue in Multi-Modal Systems, Kloster Irsee, Germany, 1999.
95. R. A. Render and H. F. Walker, "Mixture densities, maximum likelihood and the EM algorithm," SIAM Rev., vol. 26, no. 2, pp. 195-239, 1984.
96. L. Rigazio, J.-C. Junqua, and M. Galler, "Multilevel discriminative training for spelled word recognition," in Proc. IEEE ICASSP'98, 1998, pp. 489-493.
97. A. E. Rosenberg et al., "The use of cohort normalized scores for speaker verification," in Proc. ICSLP'92, 1992, pp. 599-602.
98. H. Robbins and S. Monro, "A stochastic approximation method," Ann. Math. Statist., vol. 22, pp. 400-407, 1951.
99. R. C. Rose, B.-H. Juang, and C.-H. Lee, "A training procedure for verifying string hypotheses in continuous speech recognition," in Proc. IEEE ICASSP'95, 1995, pp. 283-284.
100. M. Sugiyama and K. Kurinami, "Minimum classification error optimization for a speaker mapping neural networks," Neural Network for Signal Processing II, pp. 233-242, 1992.
101. R. Schluter and W. Macherey, "Comparison of discriminative training criteria," in Proc. IEEE ICASSP'98, 1998, pp. 493-497.
102. F. K. Soong and E.-F. Huang, "A tree-trellis based fast search for finding the N best sentence hypotheses in continuous speech recognition," in Proc. ICASSP'91.
103. R. Schluter, W. Macherey, S. Kanthak, H. Ney, and L. Welling, "Comparison on optimization methods for discriminative training criteria," in Proc. IEEE EuroSpeech'97, Sept. 1997, pp. 15-18.
104. R. Schluter, B. Mueller, F. Wessel, and H. Ney, "Interdependence of language models and discriminative training," in Proc. ASRU'99, Dec. 1999, pp. 85-89.
105. A. R. Setlur, R. A. Sukkar, and J. Jacob, "Correction recognition errors via discriminative utterance verification," presented at the Proc. IEEE ICSLP'96.
106. R. Sukkar and C.-H. Lee, "Vocabulary independent discriminative utterance verification for nonkeyword rejection in subword based speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 420-429, Nov. 1996.
107. R. Sukkar, "Subword based minimum verification error (SB-MVE) training for task independent utterance verification," Proc. IEEE ICASSP'98, pp. 229-233, 1998.
108. R. Sukkar, M. Rahim, and C.-H. Lee, "Utterance verification of keyword strings using word based minimum verification error (WB-MVE) training," in Proc. ICASSP'96, May 1996. pp. 516-519.
109. R. Sukkar, A. R. Setlur, C.-H. Lee, and J. Jacob, "Verifying and correcting string hypotheses using discriminative utterance verification," Speech Commun., vol. 22, pp. 333-342, 1997.
110. Y. Z. Tsypkin, "Self-learning-What is it?," IEEE Trans. Automat. Contr., vol. AC-13, pp. 608-612, Dec. 1968.
111. V. Wamke, S. Harbeck, E. Noth, H. Niemann, and M. Levit, "Discriminative estimation of interpolation parameters for language model classifier," in Proc. IEEE ICASSP'99, Mar. 1999, pp. 1223-1227.
112. V. Valtchev, J, J. Odell, P. C. Woodland, and S. J. Young, "Lattice-based discriminative training for large vocabulary speech recognition." in Proc. IEEE ICASSP'96, May 1996, pp. 605-608.
113. C. Yen, S.-S. KHO, and C.-H. Lee, "Minimum error rate training for phrnm-based text recognition," IEEE Trans. Image Processing, vol. 8, no. 8, pp. 1120-1124, 1999.