A survey on automatic speech recognition

IEICE Transactions on Information and Systems

Volumn E85-D, Issue 3, 2002, Pages 465-486

  Nakagawa, Seiichi ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

Acoustic model; HMM; Language model; Ngram; Speech recognition

Indexed keywords

ACOUSTIC NOISE; ARTIFICIAL INTELLIGENCE; INFORMATION THEORY; LINGUISTICS; MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH CODING; SPEECH SYNTHESIS;

ACOUSTIC MODELS; AUTOMATIC SPEECH RECOGNITION; HIDDEN MARKOV MODEL;

SPEECH RECOGNITION;

EID: 0036522866     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (237)

1. S.J. Young, M. Adda-Decker, X. Aubert, C. Dugast, J.L. Gauvain, D.J. Kershaw, L. Lamel, and D.A. Leeuwen, "Multilingual large vocabulary speech recognition in the European SQALE project," Computer Speech & Language, vol.11, pp.73-89, 1997.
2. R.P. Lippmann, "Speech recognition by machine and humans," Speech Communication. vol.22, pp.1-15, 1997.
3. S. Nakagawa, Information Theory: Fundamental and application, Kindai Kagakusha, 1992.
4. S. Nakagawa, "Capabilities and limitations of stochastic language models," Conf. Record, Acoust. Soc. Japan, pp.23-26, March 1998.
5. S. Nakagawa, "Relationship among perplexity word accuracy and phoneme accuracy, and drawback and modification of perplexity," Proc. First Int. Workshop East Asian Language Resources and Evaluation, pp.123-128, 1998.
6. W.J.J. Roberts and Y. Ephraim, "Robust speech recognition using HMM's with Toplitz state covariance matrices," Proc. ICSLP, pp.369-372, 1998.
7. S. Nakagawa, "Speech recognition based on stochastic models," Inst. Elect. Inf. Comm. Engrs., 1988.
8. S. Nakagawa, K. Shikano, and Y. Tohkura, Speech, Hearing and Neural Network Model, IOS Press, 1995.
9. N. Takubo, K. Maekawa, Y. Kubozono, K. Honda, K. Shirai, and S. Nakagawa, Speech, Iwanami-shoten, 1998.
10. S. Nakagawa, Pattern Information Processing, Maruzen, 1999.
11. K. Yamamoto and S. Nakagawa, "Relationship among speaking style, inter-phoneme's distance and speech recognition performance," Proc. ICSLP, pp.859-862, 2000.
12. S. Nakagawa, "Acoustic signal processing techniques for robust speech recognition," J. Acoust. Soc. Japan, vol.53, no.11, pp.864-871, 1997.
13. S.V. Vaseghi and B.P. Molner, "Noise compensation methods for hidden Markov model speech recognition in adverse environments," IEEE Trans. Speech Audio Process., vol.5, no.1, pp.11-21, 1997.
14. R.P. Lippmann, E.A. Martin, and D.B. Paul, "Multi-style training for robust isolated-word speech recognition," Proc. ICASSP, pp.705-708, 1987.
15. D. Pisoni, R. Bernacki, H. Nusbaum, and M. Yuchtman, "Some acoustic-phonetic correlates of speech produced in noise," Proc. ICASSP, pp.1581-1584, 1985.
16. A. Wakao, K. Takeda, and F. Itakura, "Normalizing Lombard speech under different conditions," IEICE Trans., vol.J80-D-II, no.7, pp.1643-1650, July 1997.
17. C.R. Jankowski, H.-D.H. Vo, and R.P. Lippmann, "A comparison of signal processing front ends for automatic word recognition," IEEE Trans. Speech & Audio Process., vol.3, no.4, pp.286-292, 1995.
18. J.-C. Junqua and J.P. Haton, Robustness in Automatic Speech Recognition, Kluwer Academic Pub., Dordrecht, 1996.
19. H. Hermansky and N. Morgan, "RASTA processing of speech," IEEE Trans. Speech Audio Process., vol.2, pp.578-589, 1994.
20. S. Furui, "Speaker independent isolated word recognition using dynamic features of speech spectrum," IEEE Trans. Acoust. Speech & Signal Process., vol.34, no.1, pp.52-59, 1999.
21. N. Kanadera, T. Arai, H. Hermansky, and M. Pavel, "On the relative importance of various components of the modulation spectrum for automatic speech recognition," Speech Communication, vol.28, pp.43-55, 1999.
22. C. Nadeu, P.P. Leal, and B.-H. Juang, "Filtering the time sequences of spectral parameters for speech recognition," Speech Communication, vol.22, pp.315-332, 1997.
23. Y. Nakatoh and H. Matsumoto, "An evaluation of mel-LPC cepstrum in noisy speech recognition," Conf. Record, Acoust. Soc. Japan, pp.23-24, 1999.
24. S. Omesh, L. Cohen, N. Marinovic, and D.J. Nelson, "Scale transform in speech analysis," IEEE Trans. Speech & Audio Process., vol.7, no.1, pp.40-45, 1999.
25. J. Chen, B. Xu, and T. Huang, "A novel robust feature of speech signal based on the Mellin transform for speaker-independent speech recognition," Proc. ICASSP, pp.629-632, 1998.
26. R. Singh, K. Davis, and P.V.S. Rao, "Hidden Markov model-based speech recognition with intermediate wavelet transform domains," Computer Speech and Language, vol.11, pp.252-273, 1997.
27. B.H. Juang, "Speech recognition in adverse environments," Computer Speech Language, vol.5, pp.275-294, 1991.
28. B.A. Carlson and M.A. Clements, "Speech recognition in noise using a projection based likelihood measure for mixture density HMM's," Proc. ICASSP, vol.I, pp.237-240, 1992.
29. J.-T. Chien, H.-C. Wang, and L.-M. Lee, "A novel projection-based likelihood measure for noisy speech recognition," Speech Communication, vol.24, pp.287-297, 1998.
30. S. Katagiri, B.-H. Juang, and C.-H. Lee, "Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method," Proc. IEEE, vol.86, no.11, pp.2345-2372, 1998.
31. A. Biem, E. Mcdemott, and S. Katagiri, "Discriminative feature extraction to filter design," Proc. IEEE Workshop Neural Networks for Signal Processing, vol.IV, pp.273-282, 1996.
32. K.K. Paliwal, M. Bacchiami, and Y. Sagisaka, "Minimum classification error training algorithm for feature extractor and pattern classification in speech recognition," Proc. EuroSpeech, pp.541-545, 1995.
33. T. Nitta, "Feature extraction for speech recognition based on orthogonal acoustic - Feature planes and LDA," Proc. ICASSP, pp.421-424, 1999.
34. J.A.N. Flores and S.J. Young, "Continuous speech recognition in noise using spectral subtraction and HMM adaptation," Proc. ICASSP, vol.I, pp.409-412, 1994.
35. M. Shozakai, S. Nakamura, and K. Shikano, "An evaluation of speech enhancement approach E-CMN/CSS for speech recognition," IEICE Trans., vol.J81-D, no.1, pp.1-9, Jan. 1998.
36. P. Lockwood and J. Boudy, "Experiments with a nonlinear spectral subtractor (NSS), hidden Markov model and the projection, for robust speech recognition in cars," Speech Communication, vol.11, pp.215-228, 1992.
37. D. Hardt and K. Fellbaum, "Spectral subtraction and RASTA-filtering in text-dependent HMM-based speaker verification," Proc. ICASSP, pp.867-870, 1997.
38. N. Kitaoka, I. Akahori, and S. Nakagawa, "A smoothing method of time direction on speech recognition under noisy environments using spectral subtraction," Proc. Int. Conf. Speech Processing, pp.381-386, 1999.
39. J.-L. Shen, J.-W. Hung, and L.-S. Lee, "Improved robust speech recognition considering signal correlation approximated by Tayler series," Proc. ICSLP, pp.1499-1502, 1998.
40. A.P. Varga and R.K. Moore, "Hidden Markov model decomposition of speech and noise," Proc. ICASSP, pp.845-848, 1990.
41. M.J.F. Gales and S.J. Young, "Cepstral parameter compensation for HMM recognition in noise," Speech Communication, vol.12, pp.231-239, 1993.
42. M.J.F. Gales and S.J. Young, "Robust continuous speech recognition using parallel model combination," IEEE Trans. Speech & Audio Process., vol.4, pp.352-359, 1996.
43. F. Martin, K. Shikano, Y. Minami, and Y. Okabe, "Recognition of noisy speech by composition of hidden Markov models," IEICE Technical Report, SP92-96, 1992.
44. H. Matsumoto and H. Ubukata, "Robust HMM to variation of noisy environments based on variance extension of noisy models," Proc. EuroSpeech, pp.2387-2390, 1999.
45. K.H. You and H.-C. Wang, "Robust features for noisy speech recognition based on temporal trajectory fitting of short-time autocorrelation sequences," Speech Communication, vol.28, pp.13-24, 1999.
46. K. Yamamoto and S. Nakagawa, "HMM composition of segmental unit input HMM for noisy speech recognition," Proc. EuroSpeech, pp.2865-2868, 1999.
47. K. Yamamoto and S. Nakagawa, "Difference in speech recognition performance caused by difference in front-end devices and its compensations," Proc. 7th Western Pacific Regional Acoust. Conf., pp.85-88, 2000.
48. S. Kuroiwa, T. Kato, and N. Higuchi, "Real-time cepstrum mean subtraction using the most likely partial state sequence," IEICE Trans., vol.J82-D-II, no.3, pp.332-339, March 1999.
49. A. Sankar and C.H. Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech & Audio Process., vol.4, no.5, pp.190-202, 1996.
50. K. Takagi, H. Hattori, and T. Watanabe, "Rapid environment adaptation for speech recognition," J. Acoust. Soc. Japan, (E), vol.16, no.5, pp.273-281, 1995.
51. Y. Tsurumi and S. Nakagawa, "An unsupervised speaker adaptation method for continuous parameter HMM by maximum a posteriori probability estimation," Proc. IC-SLP, pp.431-434, 1994.
52. A. Acero, "Acoustical and Environmental Robustness," in Automatic Speech Recognition, Kluwer Academic Pub., Dordrecht, 1993.
53. P.J. Moreno, B. Raj, and R.M. Stern, "Data-driven environmental compensation for speech recognition a unified approach," Speech Communication, vol.24, pp.267-285, 1998.
54. P.J. Moreno, B. Raj, and R.M. Stern, "A vector Taylor series approach for environment-independent speech recognition," Proc. ICASSP, pp.733-736, 1996.
55. D.Y. Kim, C.K. Un, and N.S. Kim, "Speech recognition in noisy environments using first-order vector Taylor series," Speech Communication, vol.24, no.1, pp.39-49, 1998.
56. Y. Minami and S. Furui, "HMM adaptation method for noise and distortion by maximizing likelihood," IEICE Trans., vol.J80-A, no.7, pp.1179-1186, July 1997.
57. M. Afify, Y. Gong, and J.P. Haton, "A general joint additive and convolutive bias approach applied to noisy lombard speech recognition," IEEE Trans. Speech & Audio Process., vol.6, no.6, pp.524-537, 1998.
58. T. Takiguchi, S. Nakamura, and K. Shikano, "HMM - Separation-based speech recognition for a distant moving speaker," IEEE Trans. Speech & Audio Process., vol.9, no.3, pp.127-140, 2001.
59. B.L. Pallon and J.H.L. Hansen, "Automatic segmentation of speech recorded in unknown noisy channel characteristics," Speech Communication, vol.25, no.1-3, pp.97-116, 1998.
60. S. Nakagawa, Y. Hirata, and Y. Hashimoto, "Japanese phoneme recognition using continuous parameter hidden Markov models," J. Acoust. Soc. Japan, vol.46, no.6, pp.486-496, June 1990.
61. V.N. Gupta, M. Lennig, and P. Mermelstein, "Integration of acoustic information in a large vocabulary word recognizer," ICASSP, vol.II, pp.697-700, 1987.
62. E. Tsuboka and J. Nakahashi, "Hidden Markov model embedded dynamic features of speech spectrum," IEICE Trans., vol.J77-A, no.2, pp.162-172, Feb. 1994.
63. E. Tsuboka and Y. Takada, "Neural predictive hidden Markov model for speech recognition," IEICE Trans., Inf. & Syst., vol.E78-D, no.6, pp.676-684, June 1995.
64. M. Saerens and H. Bourlard, "Linear and nonlinear prediction for speech recognition with hidden Markov models," Proc. EuroSpeech, pp.807-810, 1993.
65. Y.J. Chung and C.K. Un, "An MLP/HMM hybrid model using linear predictors," Speech Communication, vol.19, pp.307-316, 1996.
66. L. Deng, M. Aksmanoric, X. Sun, and C.F.J. Wu, "Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states," IEEE Trans. Speech Audio & Process., vol.2, no.4, pp.507-520, 1994.
67. Y. Hirata, I. Hayakawa, Y. Ono, and S. Nakagawa, "Speech recognition by hidden Markov model using segmental statistics," IEICE Technical Report, SP90-69, 1990.
68. S. Nakagawa, Y. Hirata, and Y. Ono, "Syllable recognition by hidden Markov model using fixed-length segmental statistics," IEICE Trans., vol.J75-D-II, no.5, pp.843-851, May 1992.
69. C.J. Wellekens, "Explicit correlation in hidden Markov model for speech recognition," Proc. ICASSP, vol.I, pp.383-386, 1987.
70. J. Ming and F.J. Smith, "Modelling of the interframe dependence in an HMM using conditional Gaussian mixtures," Computer Speech and Language, vol.10, pp.229-242, 1996.
71. K. Aikawa, H. Singer, H. Kawakara, and Y. Tohkura, "A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition," Proc. ICASSP, pp.668-671, 1993.
72. K. Yamamoto and S. Nakagawa, "Comparative evaluation of segmental unit input HMM and conditional density HMM," Proc. EuroSpeech, pp.1615-1618, 1995.
73. K. Hanai, K. Yamamoto, N. Minematsu, and S. Nakagawa, "Continuous speech recognition using segmental unit input HMM with a mixture of probability density functions and context dependency," Proc. ICSLP, pp.2935-2938, 1998.
74. S. Nakagawa and Y. Enomoto "Speaker-independent phoneme and word recognition by statistical classification methods for time-sequential patterns," IEICE Trans., vol.J71-D, no.10, pp.1977-1983, Oct. 1988.
75. K. Ide, S. Makino, and K. Kido, "Recognition on unvoiced plosive using time spectrum pattern," J. Acoust. Soc. Japan, vol.39, no.5, pp.321-329, May 1983.
76. M. Ostendorf and S. Roukos, "A stochastic segment model for phoneme-based continuous speech recognition," IEEE Trans. Acoust., Speech & Signal Process., vol.37, no.12, pp.1857-1869, 1989.
77. M. Franzini and K.-F. Lee, "Connectionist Viterbi training a new hybrid for continuous speech recognition," Proc. ICASSP, vol.I, pp.425-428, 1990.
78. S. Renal, N. Morgan, H. Bourlard, M. Cohen, and H. Franco, "Connectionist probability estimators in HMM speech recognition," IEEE Trans. Speech & Audio Process., vol.2, no.1, pp.161-174, 1994.
79. J.A. Bilmes, "Data-driven extensions to HMM statistical dependencies," Proc. ICSLP, pp.69-72, 1998.
80. P. Hanna, J. Ming, and F.J. Smith, "Inter-frame dependence arising from preceding and succeeding frames - Application to speech recognition," Speech Communication, vol.31, no.4, pp.1301-1312, 1999.
81. L.R. Bahl, P.F. Brown, P.V. Souza, and R.L. Mercer, "The IBM large vocabulary continuous speech recognition system for the ARPA NAB news task," Proc. Spoken Language Systems Technology Workshop, pp.121-126, 1995.
82. J. He and H. Leich, "A unified way in incorporating segmental feature and segmental model into HMM," Proc. ICASSP, vol.I, pp.532-535, 1995.
83. T. Ohtuki and T. Ohtomo, "The property of asymmetric segment," IEICE Technical Report, SP98-30, 1998.
84. M. Ostendonf, V.V. Digalakis, and O.A. Kimball, "From HMMs to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Speech & Audio Process., vol.4, no.5, pp.360-378, 1996.
85. J. Verhasselt, I. Illina, J.P. Martens, Y. Gong, and J.-P. Haton, "Assessing the importance of the segmentation probability in segment-based speech recognition," Speech Communication, vol.24, pp.51-72, 1998.
86. S. Rocous, M. Ostendorf, H. Gish, and A. Derr, "Stochastic segment modeling using the estimate-maximize algorithm," Proc. ICASSP, pp.127-130, 1988.
87. L. Deng and M. Aksmanovic, "Speaker-independent phonetic classification using hidden Markov models with mixtures of trend functions," IEEE Trans. Speech & Audio Process., vol.5, no.4, pp.319-324, 1997.
88. R. Chengalvara and L. Deng, "Speech trajectory discrimination using the minimum classification error learning," IEEE Trans. Speech & Audio Process., vol.6, no.6, pp.505-515, 1998.
89. W.J. Holmes and M.J. Russel, "Probabilistic-trajectory segmental HMMs," Computer Speech and Language. vol.13, pp.3-37, 1999.
90. M. Szarras and S. Matsunaga, "Improving phoneme classification performance using observation context-dependent segment models," Int. J. Speech Technology, vol.3, pp.253-262, 2000.
91. V. Digalakis, J.R. Rohlicek, and M. Ostendorf, "ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition," IEEE Trans. Speech & Audio Process., vol.1, no.4, pp.431-442, 1993.
92. M. Nakano and K. Nishiyama, Kalman-filter solved by personal computer, Maruzen 1993.
93. G. Kitagawa, Time series analysis programming, Iwanami shoten, 1993.
94. M. Afify, Y. Gong, and J.-P. Haton, "Estimation of mixtures of stochastic dynamic trajectories: Application to continuous speech recognition," Computer Speech and Language, vol.10, pp.23-36, 1996.
95. M.M. Hochberg and H.F. Silverman, "Constraining model duration variance in HMM-based connected speech recognition," Proc. EuroSpeech, pp.323-326, 1993.
96. B. Sin and J.H. Kim, "Nonstationary hidden Markov model," Signal Processing, vol.46, pp.31-46, 1995.
97. Y.K. Park, C.K. Un, and O.W. Kwon, "Modeling acoustic transitions in speech by modified hidden Markov models with state duration and state duration-dependent observation probabilities" IEEE Trans. Speech & Audio Process, vol.4, no.5, pp.389-392, 1996.
98. T. Kawahara, A. Lee, T. Kobayashi, K. Takeda, N. Minematsu, K. Itoh, A. Itoh, M. Yamamoto, A. Yamada, T. Utsuro, and K. Shikano, "Japanese dictation toolkit - 1997 version," J. Acoust. Soc. Japan, vol.E20, no.3, pp.223-239, May 1999.
99. V. Steinbiss, H. Ney, U. Essen, B.-H. Tran, X. Aubert, C. Dugast, R. Kneser, H.-G. Meier, M. Oerder, R. Haeb-Umbach, D. Geller, W. Höllerbauer, and H. Bartosik, "Continuous speech dictation - From theory to practice," Speech Communication, vol.17, pp.19-38, 1995.
100. R. Nakatsu and M. Kohda, "Recognition of spoken words based on VCV syllable unit," IEICE Trans., vol.J61-A, no.5, pp.464-471, May 1978.
101. R. Schawartz, Y. Chow, O. Kimball, S. Roucos, M. Krasner, and J. Makhoul, "Context-dependent modeling for acoustic-phonetic recognition of continuous speech," Proc., ICASSP, pp.1203-1208, 1985.
102. K.F. Lee, Automatic Speech Recognition, the Development of the SPHINX System, Kluwer Academic Publishers, 1989.
103. P.C. Woodland, C.J. Leggetter, J.J. Odell, V. Valtcher, and S.J. Young, "The 1994 HTK large vocabulary speech recognition system," Proc. ICASSP, pp.73-76, 1995.
104. S. Nakagawa, Y. Hirata, I. Murase, and T. Tanoue, "Comparison of syntax-oriented spoken Japanese understanding with semantic-oriented system," IEICE Trans., vol.E74, no.7, pp.1854-1862, July 1991.
105. T. Watanabe, "Large vocabulary word recognition based on demisyllable hidden Markov model using small amount of training data," Proc. ICASSP, S1.1, 1985.
106. T. Sakai and K. Tabata, "Multivariate statistical analysis of VCV syllables," IEICE Trans., vol.56-D, no.1, pp.63-70, Jan. 1973.
107. T. Otake, G. Hatano, G. Culter, and J. Mehler, "Mora or syllable? Speech segmentation in Japanese," J. Mem. Lang, vol.32, pp.358-378, 1993.
108. J. Hamaker, A. Ganapathiraju, J. Picone, and J.J. Godfrey, "Advances in alphadigit recognition using syllables," Proc. ICASSP, pp.421-424, 1998.
109. X.D. Xuang, Y. Ariki, and M.A. Jack, Hidden Markov model for speech recognition, Edinburgh University Press, 1990.
110. M.-Y. Hwang, and X. Huang, "Subphonetic modeling with Markov states-SENONE," Proc. ICASSP, pp.33-36, 1992.
111. V.V. Digalakis, P. Monaco, and H. Murveit, "Genones: Generalized mixture tying in continuous hidden Markov model-based speech recognizers," IEEE Trans. Speech & Audio Process., vol.4, no.4, pp.281-288, 1996.
112. S.J. Young and P.C. Woodland, "State clustering in hidden Markov-based continuous speech recognition," Computer Speech and Language, vol.8, pp.369-383, 1994.
113. S. Hayamizu and K. Tanaka, "Prediction about unknown phonetic contexts by tree-based phone modeling," Technical Report, SP90-64, IEICE 1990.
114. J. Takami and S. Sagayama, "A successive state splitting algorithm for efficient allophone modeling," Proc. ICASSP, pp.574-577, 1992.
115. T. Hori, M. Katoh, A. Itoh, and M. Kohda, "A study on HM-nets using phonetic decision tree-based successive state splitting," IEICE Trans. Inf. & Syst., vol.J80-D-II, no.10, pp.2645-2654, Oct. 1997.
116. J. Ming and J.F. Smith, "A Bayesian triphone model," Computer Speech and Language, vol.13, pp.195-206, 1999.
117. D. Rainton, and S. Sagayama, "Minimum error classification training of HMMs implementation details and experimental results," J. Acoust. Soc. Japan, vol.13, no.6, pp.379-388, 1992.
118. L.R. Bahl, P.F. Broun, P.V. Souza, and R.L. Mercer, "Estimating hidden Markov model parameters so as to maximize speech recognition accuracy," IEEE Trans. Speech & Audio Procss., vol.1, no.1, pp.77-82, 1993.
119. Y. Normndin, R. Cardin, and R. de Mori, "High performance connected digit recognition using maximum mutual information estimation," IEEE Trans. Speech & Audio Process., vol.2, pp.299-311, 1994.
120. V. Valtchev, J. Odel, P. Woodland, and S. Young, "MMIE training of large vocabulary recognition systems," Speech Communication, vol.22, pp.303-314, 1993.
121. K. Markov and S. Nakagawa, "Discriminative training of GMM using a modified EM algorithm for speaker recognition," Proc. ICSLP, vol.2, pp.177-180, 1998.
122. O.W. Kwon and C.K. Un, "Performance of HMM-based speech recognizers with discriminative state-weights," Speech Communication, vol.19, pp.197-205, 1996.
123. L.M. Arslan and H.L. Hanson, "Selective training for hidden Markov models with applications to speech classification," IEEE Trans. Speech & Audio Process., vol.7, no.1, pp.46-64, 1999.
124. K. Demuynck, J. Duchateau, D.V. Comernolle, and P. Wambacq, "Improved feature decorrelation for HMM-based speech recognition," Proc. ICSLP, pp.2907-2910, 1998.
125. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," Proc. ICASSP, pp.346-349, 1996.
126. T. Hain, P.C. Woodland, T.R. Niesler, and E.W.D. Whittaker, "The 1998 HTK system for transcription of conversational telephone speech," Proc. ICASSP, pp.57-60. 1999.
127. J.-L. Gauvain, and C.H. Lee, "Maximum aposteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech & Audio Process., vol.2, pp.291-298, 1994.
128. M.J.F. Gales and P.C. Woodland, "Mean and variance adaptation within the MLLR framework," Computer Speech and Language, vol.10, pp.249-264, 1996.
129. V.D. Diakoloukas and V.V. Digalakis, "Maximum-likelihood stochastic-transformation adaptation of hidden Markov models," IEEE Trans. Speech & Audio Process., vol.7, no.2, pp.177-187, 1999.
130. M. Padmanabham, L.R. Bahl, D. Nahamoo, and M.A. Picheny, "Speaker clustering and transformation for speaker adaptation in speech recognition systems," IEEE Trans. Speech & Audio Process., vol.6, no.1, pp.71-77, 1998.
131. K. Ohkura, M. Sugiyama, and S. Sagayama, "Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs," Proc. ICSLP, pp.369-372, 1992.
132. S. Takahashi and S. Sagayama, "Speaker adaptation of acoustic models using correlations of transfer vectors," IEICE Trans., vol.J82-D-II, no.3, pp.324-331, March 1999.
133. K. Shinoda and T. Watanabe, "Speaker adaptation with autonomous control using tree structure," Proc. Euro-Speech, pp.1143-1146, 1995.
134. V.V. Digalakis and L.G. Neumeyer, "Speaker adaptation using combined transformation and Bayesian methods," IEEE Trans. Speech & Audio Process., vol.4, no.4, pp.249-300, 1996.
135. M. Tonomura, T. Kosaka, and S. Matsumura, "Speaker adaptation using maximum a posteriori probability estimation and data size dependent parameter smoothing," IEICE Trans., vol.J81-D-II, no.3, pp.465-471, March 1998.
136. K. Shinoda and C.H. Lee, "A structural Bayes approach to speaker adaptation," IEEE Trans. Speech & Audio Process., vol.9, no.3, pp.276-287, 2001.
137. S. Nakagawa, "Automatic speech recognition by stochastic approaches," J. Acoust. Soc. Japan, vol.50, no.2, pp.126-132, Feb. 1994.
138. S. Nakagawa and K. Ohtani, "Automatic learning of stochastic context-free grammar for spontaneous speech by integration of bigram," Trans. Inf. Process. Soc. Japan, vol.39. no.3, pp.575-584, March 1998.
139. K. Ohtsuki, K. Yoshida, T. Matsuoka, and S. Furui, "A study of large-vocabulary continuous speech recognition using higher order n-gram language models," Conf. Record. Acoust. Soc. Japan. pp.47-48, Spring 1997.
140. E.P. Giachin, "Phrase bigrams for continuous speech recognition," Proc. ICASSP, pp.225-227, 1995.
141. Y. Wada, N. Kobayashi, Y. Nakano and T. Kobayashi, "Effect of vocabulary extension using word sequence concatenation for large vocabulary continuous speech recognition," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1413-1420, April 1999.
142. S. Nakagawa, H. Akamatsu, and H. Nishizaki, "A task adaptation method and use of idiomatic expression of stochastic language model for speech recognition," Natural Language Processing, vol.6, no.2. pp.97-115, Jan. 1999.
143. S. Deligned and F. Bimbot, "Language modeling by variable length sequences, theoretical formulation and evaluation of multigrams," Proc. ICASSP, pp.169-172, 1995.
144. H. Masataki and Y. Sagisaka, "Variable-order N-gram generation by word-class splitting and consecutive word grouping," Proc. ICASSP, pp. 188-191, 1996.
145. L.R. Bahl, P.F. Brown, P.V. Souza, and R.L. Mercer, "Tree-based statistical language model for natural language speech recognition," IEEE Trans. Acoust. Speech & Signal Process., vol.37, no.7, pp. 1001-1008. 1989.
146. S. Mori, M. Nishimura, and N. Itoh, "Word clustering for class-based language models," Trans. Inf. Process. Soc. Japan, vol.38, no.11, pp.2200-2207, 1997.
147. T.R. Niesler and P.C. Woodland, "Variable-length category n-gram language models," Computer Speech and Language, vol.13, pp.99-124, 1999.
148. S. Mori, and O. Yamaji, "An estimation of an upper bound for the entropy of Japanese," Trans. Inf. Process. Soc. Japan, vol.38, no.11, pp.2191-2199, 1997.
149. R. Rosenfeld, "A maximum entropy approach to adaptive statistical language modeling," Computer Speech and Language, vol.10, pp.187-228, 1996.
150. Z.G. Dong, and L.K. Teng, "Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition," Computer Speech and Language, vol.13, pp.125-141, 1999.
151. J.R. Bellegard, "A multispan language model modeling framework for large vocabulary speech recognition," IEEE Trans. Acoust. Speech & Signal Process., vol.6, no.5, pp.456-467, 1998.
152. J.R. Bellegard, "Multispan statistical language modeling for large vocabulary speech recognition," Proc. ICSLP, pp.2395-2398, 1998.
153. R.M. Iyer and M. Ostendorf, "Modeling long distance dependence in language: Topic mixtures versus dynamic cache models," IEEE Trans. Speech & Audio Process., vol.7, no.1, pp.31-39, 1997.
154. S. Martin, J. Liermann, and H. Ney, "Adaptive topic-dependent language modeling using word-based varigramss," Proc. EuroSpeech, pp.1447-1450, 1997.
155. K. Takagi and S. Furui, "Dictation of broadcast news speech using word pronounciation probability," Conf. Record, Acoust. Soc. Japan, pp.9-10, Spring 1998.
156. N. Sakurai and S. Furui, "An improvement of language modeling for automatic transcription of Japanese broadcast-news speech," Conf. Record, Acoust. Soc. Japan, pp.57-58, Spring 1999.
157. T. Imai, Y. Saito, A. Ando, and S. Furui, "A language model for recognition of continuously uttered sentences," Conf. Record, Acoust. Soc. Japan, pp.63-64, Spring 1999.
158. A. Kobayashi, T. Imai, A. Ando, and K. Nakabayashi, "Time dependent language model for broadcast news transcription," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1421-1429, April 1999.
159. N. Yodo, K. Itoh, S. Nakamura, and K. Shikano, "The influence of morpheme analysis systems on language model for continuous speech recognition," Conf. Record, Acoust. Soc. Japan, pp.53-54, Autumn 1997.
160. S.F. Chen and J. Goodman, "An empirical study of smoothing techniques for language modeling," Proc. ACL, pp.310-318, 1996.
161. M. Zhou and S. Nakagawa, "Succeeding word prediction for speech recognition based on stochastic language model," IEICE Trans. Inf. & Syst., vol.E79-D, no.4, pp.333-341, April 1996.
162. F. Pereira and Y. Schabes, "Inside-outside reestimation from partially bracketed corpora," Proc. ACL, pp.31-37, 1992.
163. R. Hwa, "An empirical evaluation of probabilistic lexicalized tree insertion grammars," Proc. ACL, pp.557-563, 1998.
164. C. Hori, M. Katoh, A. Itoh, and M. Kohda, "Construction and evaluation of language models based on stochastic context free grammar for speech recognition," Technical Report, SP99-37, Inst. Elect. Inf. Comm. Engrs., June 1999.
165. M. Zuzuki and S. Makino, "An automatic acquisition method of statistical finite-state automation sentences," Proc. ICASSP, pp.737-740, 1999.
166. H. Imai, H. Tanaka, and T. Tokunaga, "Construction of language models using probabilistic GLR methods toward speech recognition," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1404-1411, April 1999.
167. H. Tsuboi, Y. Takebayashi, and H. Hashimoto, "Spontaneous speech understanding method based on LR parsing of keyword lattice," Trans. Inf. Process. Soc. Japan, vol.38, no.2, pp.260-268, Feb. 1997.
168. J.G. Wilpon, L.R. Rabiner, C.-H. Lee, and E.R. Goldman, "Automatic recognition of keywords in unconstrained speech using hidden Markov models," IEEE Trans. Acoust. Speech & Signal Process., vol.38, no.11, pp.1870-1878, 1990.
169. K. Kita, T. Ehara, and T. Morimoto, "Processing unknown words in continuous speech recognition," IEICE Trans, vol.E74, no.7, pp.1811-1816, July 1991.
170. J. Ogata and Y. Ariki, "Comparison of dictation and word spotting techniques in classification of news speech articles," IEICE Technical Report, SP98-32, June 1998.
171. T. Kawahara, K. Ishizuka, and S. Doshita, "Voice-operated projector using utterance verification and its application to hyper-text generation of lectures," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1491-1498, April 1999.
172. A. Kai, Y. Hirose, and S. Nakagawa, "Dealing with out-of -vocabulary words and speech disfluencies in an N-gram based speech understanding system," Proc. ICSLP, pp.2427-2430, Dec. 1999.
173. B. Chen, H. Wong, L. Chen, and L. Lee, "A*-admissible key-phrase spotting with sub-syllable level utterance verification," Proc. ICSLP, pp.783-786, 1998.
174. Q. Lin, S-Das, D. Lubensky, and M. Picheny, "A new confidence measure based on rank-ordering subphone scores," Proc. ICSLP, pp.3249-3252, 1998.
175. K.P. Markov, and S. Nakagawa, "Text-independent speaker recognition using non-linear frame likelihood transformation," Speech Communication, vol.24, pp.193-209, 1998.
176. M. Nishimura, N. Itoh, and K. Yamasaki, "Word-based approach to large-vocabulary continuous speech recognition for Japanese," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1395-1403, April 1999.
177. T. Watanabe and S. Tsukada, "Unknown utterance rejection using likelihood normalization based on syllable recognition," IEICE Trans., vol.J75-D-II, no.12, pp.2002-2009, Dec. 1992.
178. A. Kai, and S. Nakagawa, "Relationship among recognition rate, rejection rate and false alarm rate in a spoken word recognition system," IEICE Trans. Inf. & Syst., vol.E78-D, no.6, pp.698-704, June 1995.
179. J.-L. Gauvain and L. Lamel, "Large vocabulary continuous speech recognition: From laboratory systems towards real-world applications," IEICE Trans., vol.J79-D-II, no.12, pp.2005-2021, Dec. 1996.
180. T. Imai, K. Onoe, A. Kobayashi, and A. Ando, "A decoder for broadcast news transcription," Acoust. Soc. Japan, pp.105-106, Autumn 1998.
181. S. Nakagawa and H. Akamatsu, "A new computation method of perplexity for text corpus including unknown words," Conf. Record, Acoust. Soc. Japan, pp.63-64, Autumn 1998.
182. H. Masataki, Y. Sagisaka, K. Hisaki, and T. Kawahara, "Task adaptation using MAP estimation in N-gram language modeling," Proc. ICASSP, pp.783-786, 1997.
183. S. Nakagawa, "Relationship between phoneme recognition performance and word recognition rate," Trans. Inf. Process, Japan, vol.22, no.5, pp.488-496, May 1996.
184. M. Hidano, T. Itoh, M. Yamamoto, and S. Nakagawa, "Spontaneous speech understanding for a dialogue system," Proc. ESCA Workshop on Spoken Dialogue Systems, pp.25-28, 1995.
185. S. Nakagawa and M. Sakamoto, "Evaluation of FFT cepstrum and LPC cepstrum for speech and speaker recognition," IEICE Trans., vol.J66-A, no.2, pp.1199-1206, Feb. 1983.
186. H. Kuwabara and H. Sakai, "Perception of vowels and C-V syllables segmented from connected speech," J. Acoust. Soc. Japan, vol.28, no.5, pp.225-234, May 1972.
187. K. Yamamoto and S. Nakagawa, "A study on speech recognition unit based on speech perceptual experiments," IEICE Technical Report, SP99-43, July 1999.
188. S. Nakagawa, "Toward spoken language understanding from speech recognition," J. Acoust. Soc. Japan, vol.52, no.11, pp.859-856, Nov. 1996.
189. K. Obara and T. Hirahara, "Evaluation of auditory front-ends in DTW word recognition system," J. Acoust. Soc. Japan, vol.50, no.6, pp.452-464, June 1994.
190. J. Billa, T. Colhurst, A. El-Jaroudi, R. Iyer, K. Ma, S. Matsuoukas, C. Quilen, F. Richardson, M. Siu, G. Zavaligkos, and H. Gish, "Recent experiments in large vocabulary conversational speech recognition," Proc. ICASSP, pp.41-44, 1999.
191. P. McCourt, S. Vaseghi, and N. Harte, "Multiresolution cepstral features for phoneme recognition across speech sub-bands," Proc. ICASSP, pp.557-560, 1998.
192. S. Kong and B. Shi, "Channel and noise adaptation via HMM mixture mean transform and stochastic matching," Proc. ICASSP, pp. 301-304, 1999.
193. P. Kenny, M. Lenning, and P. Mermelstein, "A linear predictive HMM for vector valued observation with application to speech recognition," IEEE Trans. Acoust. Speech & Signal Process., vol.38, no.1, pp.220-225, 1990.
194. S. Nakagawa, "Proposal of a stochastic context-free grammar for continuous observation vector sequences," Conf. Record, pp.73-74, Spring 1992.
195. Y. Zhao, L.E. Atlas, and X. Zhuang, "Application of the Gibbs distribution to hidden Markov modeling in speaker independent isolated word recognition," IEEE Trans. Signal Process., vol.39, no.6, pp.1291-1298, 1991.
196. G. Zweig and S. Russel, "Probabilistic modeling with Bayesian networks for automatic speech recognition," Proc. ICSLP, pp.3011-3014, 1998.
197. S. Nakagawa, L. Zhao, and H. Suzuki, "A comparative study of output probability functions in HMMs," IEICE Trans. Inf. & Syst., vol.E78-D, no.6, pp.669-675, June 1995.
198. H. Singer and A. Nakamura, "Unified framework for acoustic topology modelling: ML-SSS and question-based decision trees," Proc. EuroSpeech, pp.1355-1358, 1999.
199. S. Furui, "Learning and normalizing of the talker differences in the recognition of spoken words," Technical Report, Acoust. Soc. Japan, SP75-25, Nov. 1975.
200. S. Nakagawa and T. Sakai, "A real time spoken word recognition system with various learning capabilities of the speaker differences," Syst. Comp. Controls, vol.9, no.3, pp.63-71, Scripta Publishing Co., 1978.
201. M. Owens, A. Kruger, P. Donnelly, F.J. Smith, and J. Ming, "A missing-word test comparison of human and statistical language model performance," Proc. EuroSpeech, pp.145-148, 1999.
202. Y. Wada, N. Kobayashi, and T. Kobayashi, "Robust language modeling for small corpus of target task using call combined word statistics and selective use of general corpus," IEICE Trans., vol.J83-D-II, no.11, pp.2397-2406, Nov. 2000.
203. H. Yamamoto, and Y. Sagisaka, "Part-of-speech N-gram and word N-gram fused language model," Proc. Euro-Speech, pp.1803-1806, 1999.
204. S. Ortmanns, H. Ney, and Z. Aubert, "A word graph algorithm for large vocabulary continuous speech recognition," Computer Speech and Language, vol.11, pp.43-72, 1997.
205. T. Hori, N. Oka, M. Katoho, A. Itoh, and M. Kohda, "A study on a phoneme-graph-based hypothesis restriction for large vocabulary continuous speech recognition," Trans. Inf. Process. Soc. Japan, vol.40, no.4, pp.1365-1373 April 1999.
206. A. Lee, Kawahra, and S. Doshita, "Large vocabulary continuous speech recognition based on multi-pass search using word trellis index," IEICE Trans., vol.J82-D, no.1, pp.1-9, Jan. 1999.
207. S. Nakagawa, "Some problems on automatic speech recognition," IEICE Technical Report, SP99-93, Dec. 1999.
208. A. Ogawa, K. Takeda, and F. Itakura, "Balancing acoustic and linguistic probabilities," Proc. ICASSP, pp.181-184, 1998.
209. T. Kobayashi, J. Furuyama, and K. Masumitsu, "Partly hidden Markov model and its application to speech recognition," Proc. ICASSP, pp.121-124, 1999.
210. M. Zhou and S. Nakagawa, "Comparison of SCFG and HMM based speaker independent spoken digit recognition," Proc. Int. Workshop on Automatic Speech Recognition, pp.30-31, Dec. 1993.
211. H. Ney and S. Ortmanns, "Dynamic programming search for continuous speech recognition," IEEE Signal Process. Mag., pp.64-82, Sept. 1999.
212. N. Deshmukh, A. Ganapathiraju, and J. Picone, "Hierarchical search for large-vocabulary conversational speech recognition," IEEE Signal Process. Mag., pp.84-107, Sept. 1999.
213. R. Kompei, Prosody in Speech Understanding Systems, Springer, 1996.
214. D.P. Morgan and C.L. Scofield, Neural Networks and Speech Processing, Kluwer Academic Publishers, 1994.
215. H.A. Boarlard and N. Morgan, Connectionist Speech Recognition, Kluwer Academic Publishers, 1994.
216. H. Singer and S. Sagayama, "Pitch dependent phone modeling for HMM-based speech recognition," J. Acoust. Soc. Japan, (E), vol.15, no.2, pp.77-86, 1994.
217. N. Minematsu and S. Nakagawa, "Modeling of variations in cepstral coefficients caused by F0 changes and its application to speech processing," Proc. ICSLP, pp.2427-2430, Dec. 1998.
218. A.J. Robinson, "An application of recurrent nets to phone probability estimation," IEEE Trans. Neural Networks, vol.5, no.2, pp.298-304, 1994.
219. S. Nakagawa, "Speech understanding and language model," J. Signal Process., vol.2, no.6, pp.434-442, Nov. 1998.
220. S. Nakagawa, "Introduction to the special issue-some research problems on spoken dialogue systems," J. Acoust. Soc. Japan, vol.54, no.11, pp.783-790, Nov. 1998.
221. R.D. Mori, ed., Spoken Dialogue with Computers, Academic Press, 1998.
222. T. Matsui, "HMM-based speaker recognition," IEICE Technical Report, SP95-111, Jan. 1996.
223. J.P. Campbell, "Speaker recognition: A tutorial," Proc. IEEE, vol.85, no.9, 1437-1462, 1997.
224. S. Furui, Digital Speech Processing, Synthesis and Recognition, Marcel Dekker, 1989.
225. S. Imai, Speech Signal Processing, Morikita-shuppan, 1996.
226. K. Kita, S. Nakamura, and M. Nagata, Spoken language processing, Morikita-shuppan, 1996.
227. K. Shikano, S. Nakamura, and S. Ise, Digital Signal Processing for Speech and Sound, Shokodo, 1997.
228. H. Tanaka, ed., Natural Language Processing - Fundamental and application -, IEICE, 1999.
229. K. Fukunaga, Statistical Pattern Recognition, Second Edition, Academic Press, 1990.
230. S. Furui and M.M. Sondhi, Advances in Speech Signal Processing, Dekker, 1991.
231. E. Charniak, Statistical Language Learning, MIT Press, 1993.
232. J.R. Deller, J.G. Proakis, and J.H.L. Hansen, Discrete-Time Processing of Speech Signals, Macmillan, 1993.
233. L.R. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition, Prentice Hall, 1993.
234. C.H. Lee, F.K. Soong, and K.K. Paliwal, Automatic Speech and Speaker Recognition, Kluwer Academic Pub., 1996.
235. F. Jelinek, Statistical Methods for Speech Recognition, MIT Press, 1997.
236. L.E. Shannon, "Prediction and entropy of printed English," Bell System Tech. J., vol.30, pp.50-64, 1951.
237. T.M. Cover and R.C. King, "A covergent gambling estimate of the entropy of English," IEEE Trans. Inf. Theory, vol.24, no.4, pp.413-421, 1978.