On stochastic feature and model compensation approaches to robust speech recognition

Speech Communication

Volumn 25, Issue 1-3, 1998, Pages 29-47

  Lee, Chin Hui ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DISTORTION (WAVES); ERROR COMPENSATION; MATHEMATICAL MODELS; PARAMETER ESTIMATION; RANDOM PROCESSES; ROBUSTNESS (CONTROL SYSTEMS);

MODEL COMPENSATION;

SPEECH RECOGNITION;

EID: 0032140546     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(98)00028-4     Document Type: Article

References (77)

1. Abrash, V., Sankar, A., Franco, H., Cohen, M., 1996. Acoustic adaptation using non-linear transformations of HMM parameters. In: Proceedings of ICASSP-96, Atlanta, pp. 729-732.
2. Acero, A., 1992. Acoustical and Environmental Robustness in Automatic Speech Recognition. Kluwer Academic Publishers, Dordrecht.
3. Atal, B., 1974. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. Journal of Acoustic Society of America 55, 1304-1312.
4. Bahl, L.R., Jelinek, F., Mercer, R.L., 1983. A maximum likelihood approach to continuous speech recognition. IEEE Transactions on Pattern Analysis, Machine Intelligence 5, 179-190.
5. Baum, L., Petrie, T., Soules, G., Weiss, N., 1970. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. The Annals of Mathematical Statistics 41 (1), 164-171.
6. Chien, J.-T., Lee, L.-M., Wang, H.-C., 1996. Noisy speech recognition using variance adapted likelihood measure. In: Proceedings of ICASSP-9, Vol. 6, Atlanta, pp. 45-48.
7. Chien, J.-T., Lee, C.-H., Wang, H.-C., 1997. A hybrid algorithm for speaker adaptation using MAP transformation and adaptation. IEEE Signal Processing Letters 4 (6), 167-169.
8. Chou, W., Rahim, M., Buhrke, E., 1995. Signal conditioned minimum error rate training for continuous speech recognition. In: Proceedings of EuroSpeech-95, Madrid.
9. Cox, S.J., 1995. Predictive speaker adaptation in speech recognition. Computer Speech and Language 9 (1), 1-17.
10. Cox, S.J., Bridle, J., 1989. Unsupervised speaker adaptation by probabilistic spectrum fitting. In: Proceedings of ICASSP-89, Glasgow, pp. 294-297.
11. Cox, S.J., Bridle, J., 1990. Simultaneous speaker normalisation and utterance labelling using Bayesian/neural net techniques. In: ICASSP-90, Albuquerque, pp. 161-164.
12. Das, S., Bakis, R., Nadas, A., Nahamoo, D., Picheny, M., 1993. Influence of background noise and microphone on the performance of the IBM TANGORA speech recognition system. In: Proceedings of ICASSP-93, Minneapolis, pp. II-71-74.
13. Dempster, A., Laird, N., Rubin, D., 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of Royal Statistical Soceity 39 (1), 1-38.
14. Digalakis, V., Neumeyer, L., 1996. Speaker adaptation using combined transformation and Bayesian methods. IEEE Transactions on Speech and Audio 4 (4), 294-300.
15. Ephraim, Y., 1992a. Gain-adapted hidden Markov models for recognition of clean and noisy speech. IEEE Transactions on Signal Processing 40 (6), 1303-1316.
16. Ephraim, Y., 1992b. Statistical model based speech enhancement systems. Proceedings of IEEE 80 (10), 1526-1555.
17. Erell, A., Weintraub, M., 1993. Energy-conditioned spectral estimation for recognition of noisy speech. IEEE Transactions on Speech and Audio 1 (1), 84-89.
18. Flanagan, J.L., 1972. Speech Analysis, Synthesis and Perception, 2nd ed. Springer, Berlin.
19. Furui, S., 1980. A training procedure for isolated word recognition systems. IEEE Transactions on Acoustics, Speech, Signal Processing 28 (2), 129-136.
20. Furui, S., 1986. Speaker-independent isolated word recognition using dynamic features of speech spectrum. IEEE Transactions on Acoustics, Speech and Signal Processing 34 (1), 52-59.
21. Furui, S., 1989. Unsupervised speaker adaptation method based on hierarchical spectral clustering. In: Proceedings of ICASSP-89, Glasgow, pp. 286-289.
22. Furui, S., 1997. Recent advances in robust speech recognition. In: Proceedings of ESCA Workshop on Robust Speech Recognition, Pont-a-Mousson, France.
23. Gales, M.J.F., Young, S.J., 1995. Robust speech recognition in additive and convolutional noise using parallel model combination. Computer Speech and Language 9, 289-307.
24. Gauvain, J.-L., Lee, C.-H., 1992. Bayesian learning for hidden Markov models with Gaussian mixture state observation densities. Speech Communication 11 (2-3), 205-213.
25. Gauvain, J.-L., Lee, C.-H., 1994. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio 2 (2), 291-298.
26. Hanson, B.A., Applebaum, T.H., Junqua, J.-C., 1996. Spectral dynamics for speech recognition under adverse conditions. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 14. Kluwer Academic Publishers, Dordrecht.
27. Hattori, H., Sagayama, S., 1992. Vector field smoothing principle for speaker adaptation. In: Proceedings of ICSLP-92, Banff, pp. 381-384.
28. Hermansky, H., Morgan, N., Bayya, A., Kohn, P., 1971. Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP). In: Proceedings of EuroSpeech-91, pp. 1367-1370.
29. Holmes, J., Sedgwick, N., 1986. Noise compensation for speech recognition using probabilistic models. In: Proceedings of ICASSP-86, Tokyo.
30. Huo, Q., Lee, C.-H., 1996. On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition. In: Proceedings of ICSLP-96, Philadelphia, pp. 981-984.
31. Huo, Q., Lee, C.-H., 1997. On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate. IEEE Transactions on Audio and Speech Processing 5 (2), 161-172.
32. Huo, Q., Chan, C., Lee, C.-H., 1995. Bayesian adaptive learning of the parameters of hidden Markov model for speech recognition. IEEE Transactions on Speech and Audio Processing 3 (5), 334-345.
33. Huo, Q., Jiang, H., Lee, C.-H., 1997. A Bayesian predictive classification approach to robust speech recognition. In: Proceedings of ICASSP-97, Munich, pp. 1549-1550.
34. Juang, B.-H., 1985. Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains. AT&T Technical Journal 64 (6), 1235-1249.
35. Juang, B.-H., 1991. Speech recognition in adverse environments. Computer Speech and Language 5, 275-294.
36. Juang, B.-H., Chou, W., Lee, C.-H., 1996. Statistical and discriminative methods for speech recognition. In: Lee, C.-H., Soong, K.K., Paliwal, F.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 5. Kluwer Academic Publishers, Dordrecht.
37. Junqua, J.-C., Anglade, Y., 1990. Acoustic and perceptual studies of Lombard speech: Application to isolated-words automatic speech recognition. In: Proceedings of ICASSP-90, Albuquerque, pp. 841-844.
38. Lee, C.-H., Gauvain, J.-L., 1996. Bayesian adaptive learning and MAP estimation of HMM. In: Lee, C.-H., Soong, F.K., Paliwal K.K. (Eds.), Speech and Speaker Recognition: Advanced Topics, Chapter 4. Kluwer Academic Publishers, Dordrecht.
39. Lee, C.-H., Lin, C.-H., 1993. On the use of a family of signal limiters for recognition of noisy speech. Speech Communication 12, 383-392.
40. Lee, C.-H., Lin, C.-H., Juang, B.-H., 1991. A study on speaker adaptation of the parameters of continuous density hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing 39 (4), 806-814.
41. Leggetter, C.J., Woodland, P.C., 1995. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language 9, 171-185.
42. Levinson, S.E., 1985. Structural methods in automatic speech recognition. Proceedings of IEEE 73, 1625-1650.
43. Liu, F.-H., Acero, A., Stern, R.M., 1992. Efficient joint compensation of speech for the effect of additive noise and linear filtering. In: Proceedings ICASSP-92, San Francisco, pp. I-257-260.
44. Mansour, D., Juang, B.-H., 1989. A family of distortion measures based upon projection operation for robust speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 37, 1659-1671.
45. Matsuoka, T., Lee, C.-H., 1993. A study of on-line Bayesian adaptation for HMM-based speech recognition. In: Proceedings of EuroSpeech-93, Berlin, pp. 815-818.
46. Merhav, N., Lee, C.-H., 1993. A minimax classification approach with application to robust speech recognition. IEEE Transactions on Speech and Audio 1 (1), 90-100.
47. Minami, Y., Furui, S., 1995. A maximum likelihood procedure for a universal adaptation method based on HMM composition. In: Proceedings ICASSP-95, Detroit, pp. I-129-133.
48. Moon, S., Hwang, J.-N., 1995. Robust speech recognition using robust inversion of HMMs. In: Proceedings of ICASSP-95, Detroit, pp. I-145-148.
49. Moreno, P.J., Raj, B., Stern, R.M., 1996. A vector Taylor series approach for environment-independent speech recognition. In: Proceedings of ICASSP-96, Atlanta, pp. 733-736.
50. Nadas, A., Nahamoo, D., Picheny, M., 1988. Speech recognition using noise-adaptive prototypes. In: Proceedings ICASSP-88, New York, pp. 517-520.
51. Neumeyer, L., Weintraub, M., 1994. Probabilistic optimum filtering for robust speech recognition. In: Proceedings of ICASSP-94, Adelaide, pp. I-417-420.
52. Ney, H., 1996. Dynamic programming search strategies: From digit strings to large vocabulary word graphs. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 16. Kluwer Academic Publishers, Dordrecht.
53. Normandin, Y., 1996. Maximum mutual information estimation of hidden Markov models. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 3. Kluwer Academic Publishers, Dordrecht.
54. Ohkura, K., Sugiyama, M., Sagayama, S., 1992. Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs. In: Proceedings of ICSLP-92, Banff, pp. 369-372.
55. Ostendorf, M., Digalakis, V.V., Kimball, O.A., 1996. From HMM's to segment models: A unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing 4 (5), 360-378.
56. Rabiner, L.R., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of IEEE 77 (2), 257-286.
57. Rabiner, L.R., Juang, B.-H., Lee, C.-H, 1996. An overview of automatic speech recognition. In: Lee, C.-H., Soong, F.K., Paliwal, K.K., (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 1. Kluwer Academic Publishers, Dordrecht.
58. Rahim, M., Juang, B.-H., 1996. Signal bias removal by maximum likelihood estimation for robust telephone speech recognition. IEEE Transactions on Speech and Audio Processing 4 (1), 19-30.
59. Rajasekaran, P.K., Doddington, G.R., Picone, J.W., 1986. Recognition of speech under stress and in noise. In: Proceedings of ICASSP-86, Tokyo, pp. 733-736.
60. Rose, R.C., Hofstetter, E.M., Reynolds, D.A., 1994. Integrated models of speech and background with application to speaker identification in noise. IEEE Transactions on Speech and Audio 2, 245-257.
61. Rozzi, W.A., Stern, R.M., 1991. Speaker adaptation in continuous speech recognition via estimation of correlated mean vectors. In: Proceedings of ICASSP-91, Toronto, pp. 865-868.
62. Sankar, A., Lee, C.-H., 1996. A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Transactions on Audio and Speech Processing 4 (3), 190-202.
63. Schwartz, R., Nguyen, L., Makhoul, J., 1996. Multiple-pass search strategies. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 18. Kluwer Academic Publishers, Dordrecht.
64. Siohan, O., Lee, C.-H., 1997. Iterative noise and channel estimation under the stochastic matching algorithm framework. IEEE Signal Processing Letters, to appear.
65. Soong, F.K., Rosenberg, A.E., 1988. On the use of instantaneous and transitional spectral information in speaker recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 36 (6), 871-879.
66. Stern, R.M., Lasry, M.J., 1987. Dynamic speaker adaptation for feature-based isolated word recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 35 (6), 751-763.
67. Stern, R.M., Acero, A., Liu, F.-H., Ohshima, Y., 1996. Signal processing for robust speech recognition. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition: Advanced Topics, Chapter 15. Kluwer Academic Publishers, Dordrecht.
68. Surendran, A.C., Lee, C.-H., Rahim, M., 1996. A maximum likelihood stochastic matching approach to non-linear equalization for robust speech recognition. In: Proceedings of ICSLP-96, Philadelphia, pp. 1832-1835.
69. Takagi, K., Hattori, H., Watanabe, T., 1994. Speech recognition with rapid environment adaptation by spectrum equalization. In: Proceedings of ICSLP-94, Yokohama, pp. 1023-1026.
70. Takahashi, J.-I., Sagayama, S., 1995. Vector-field-smoothed Bayesian learning for incremental speaker adaptation. In: Proceedings of ICASSP-95, Detroit, pp. I-696-699.
71. Tonomura, M., Kosaka, T., Matsunaga, S., 1995. Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation. In: Proceedings of ICASSP-95, Detroit, pp. I-688-691.
72. Van Compernolle, D., 1989. Noise adaptation in a hidden Markov model speech recognition system. Computer Speech and Language 3, 151-167.
73. Varga, A., Moore, R., 1990. Hidden Markov model decomposition of speech and noise. In: Proceedings of ICASSP-90, Albuquerque, pp. 845-848.
74. Varga, A., Moore, R., Bridle, J., Ponting, K., Russell, M., 1988. Noise compensation algorithms for use with hidden Markov model based speech recognition. In: Proceedings of ICASSP-88, New York, pp. 481-484.
75. Zavaliagkos, G., Schwartz, R., Makhoul, J., 1995. Batch, incremental and instantaneous adaptation techniques for speech recognition. In: Proceedings of ICASSP-95, Detroit, pp. I-676-679.
76. Zhao, Y., 1993. A new speaker adaptation technique using very short calibration speech. In: Proceedings of ICASSP-93, Minneapolis, pp. II-562-565.
77. Zhao, Y., 1995. Iterative self-learning speaker and channel adaptation under various initial conditions. In: Proceedings of ICASSP-95, Detroit, pp. I-712-715.