Towards increasing speech recognition error rates

Speech Communication

Volumn 18, Issue 3, 1996, Pages 205-231

  Bourlard, Hervé ^a,b   Hermansky, Hynek ^b,d   Morgan, Nelson ^a,c  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b FACULTÉ POLYTECHNIQUE DE MONS   (Belgium)

^c UNIVERSITY OF CALIFORNIA   (United States)

^d OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUDITION; DECODING; ERROR CORRECTION; FEATURE EXTRACTION; SPEECH PROCESSING;

AUTOMATIC SPEECH RECOGNITION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 0030142722     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-6393(96)00003-9     Document Type: Article

References (106)

1. S.M. Ahadi and P.C. Woodland (1995), "Rapid speaker adaptation using model prediction", Proc. IEEE Internat. Conf. Acoust. Speech, Detroit, MI, pp. 684-687.
2. L. Aitkin, C. Dunlop and W. Webster (1966), "Click-evoked response patterns of single units in the medial geniculate body of the cat", J. Neurophysiology, Vol. 29, pp. 109-123.
3. K. Aikawa, H. Singer, H. Kawahara and Y. Tohkura (1993), "A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Minneapolis, MN, pp. II-668-671.
4. J.B. Allen (1994), "How do humans process and recognize speech?", IEEE Trans. Speech Audio Process., Vol. 2, No. 4, pp. 567-577.
5. A. Anastasakos, F. Kubala, J. Makhoul and R. Schwartz (1994), "Adaptation to new microphones using tied-mixture normalization", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Adelaide, Australia, pp. I-433-437.
6. T.H. Applebaum and B.A. Hanson (1991), "Regression features for recognition of speech in quiet and in noise", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Toronto, Canada, pp. 985-989.
7. A. Asadi, R. Schwartz and J. Makhoul (1990), "Automatic detection of new words in a large vocabulary continuous speech recognition system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, pp. 125-128.
8. S. Austin, G. Zavaliagkos, J. Makhoul and J. Schwartz (1992), "Improving state-of-the-art continuous speech recognition systems using the N-best paradigm with neural networks", Proc. DARPA Speech and Natural Language Workshop, Harriman, NY (Morgan Kaufmann, Los Altos, CA), pp. 180-184.
9. L.R. Bahl, P.P. Brown, P.V. de Souza and R.L. Mercer (1988), "A new algorithm for the estimation of hidden Markov models", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., New York, NY, pp. 493-496.
10. J.K. Baker (1975), "The Dragon system - An overview", IEEE Trans. Acoust. Speech Signal Process., Vol. ASSP-23, No. 1, pp. 24-29.
11. Y.R. Bengio, R. De Mori, G. Flammia and R. Kompe (1992), "Global optimization of a neural-hidden Markov model hybrid", IEEE Trans. Neural Networks, Vol. 3, pp. 252-258.
12. Y. Bengio and P. Frasconi (1995), "An input output HMM architecture", in Advances in Neural Information Processing Systems, ed. by G. Tesauro, D. Touretzky and T. Leen, Vol. 7 (MIT Press, Cambridge, MA).
13. A. Bounds (1995), Personal communication.
14. H. Bourlard and C.J. Wellekens (1990), "Links between Markov models and multilayer perceptrons", IEEE Trans. Pattern Anal. Machine Intell., Vol. 12, No. 12, pp. 1167-1178.
15. H. Bourlard and N. Morgan (1994), Connectionist Speech Recognition - A Hybrid Approach (Kluwer Academic Publishers, Dordrecht).
16. H. Bourlard, Y. Konig and N. Morgan (1994), REMAP: Recursive estimation and maximization of a posteriori probabilities - Application to transition-based connectionist speech recognition, ICSI Technical Report TR94-064, Internat. Computer Science Institute, CA.
17. H. Bourlard, Y. Konig and N. Morgan (1995), "REMAP: recursive estimation and maximization of a posteriori probabilities in connectionist speech recognition", Proc. Eurospeech '95, Madrid, Spain.
18. J.S. Bridle and M.D. Brown (1974), An experimental automatic word recognition system, JSRU Report No. 1003, Ruislip, England: Joint Speech Research Unit.
19. J.S. Bridle (1995), Personal communication.
20. P. Brown, The acoustic-modelling problem in automatic speech recognition, PhD Thesis, Computer Science Department, Carnegie Mellon University.
21. J.R. Cohen (1989), "Application of an auditory model to speech recognition", J. Acoust. Soc. Amer., Vol. 85, No. 6, pp. 2623-2629.
22. J.R. Cohen (1995), Informal communication.
23. M. Cohen, H. Franco, N. Morgan, D. Rumelhart and V. Abrash (1992), "Hybrid neural network/hidden Markov model continuous speech recognition", Proc. Internat. Conf. Speech Language Processing, Banff, Canada, pp. 915-918.
24. L.A. Chistovich (1985), "Central auditory processing of peripheral vowel spectra", J. Acoust. Soc. Amer., Vol. 77, pp. 789-805.
25. S.B. Davis and P. Mermelstein (1980), "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences", IEEE Trans. Acoust. Speech Signal Process., Vol. 28, No. 4, pp. 357-366.
26. P. de La Noue, S. Levinson and M. Sondhi (1989), Incorporating the time correlation between successive observations in an acoustic-phonetic hidden Markov model for continuous speech recognition, AT&T Technical Memorandum No. 11226.
27. S. Della Pietra, V. Della Pietra, R.L. Mercer and S. Roukos (1992), "Adaptive language modelling using minimum discriminant estimation", Proc. DARPA Speech and Natural Language Workshop, Harriman, NY, pp. 103-106.
28. A.P. Dempster, N.M. Laird and D.B. Rubin (1977), "Maximum likelihood from incomplete data via the EM algorithm", J. Roy. Statist. Soc., Vol. 39, pp. 1-38.
29. L. Deng, M. Aksmanovic, X. Sun and C. Wu (1994), "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.
30. G. Doddington (1989), "Phonetically sensitive discriminants for improved speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Glasgow, Scotland, pp. 556-559.
31. P. Duchnowski (1993), A new structure for automatic speech recognition, PhD Thesis, MIT.
32. K. Elenius and M. Blomberg (1982), "Effects of emphasizing transitional or stationary parts of the speech signal in a discrete utterance recognition system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Paris, France, pp. 535-537.
33. M. Fanty, P. Schmid and R. Cole (1993), "City name recognition over the telephone", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Minneapolis, MN, pp. I-549-552.
34. M.A. Franzini, K.F. Lee and A. Waibel (1990), "Connectionist Viterbi training: A new hybrid method for continuous speech recognition", IEEE Proc. Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, pp. 425-428.
35. H. Fletcher (1953), Speech and Hearing in Communication (Krieger, New York).
36. S. Furui (1981), "Cepstral analysis technique for automatic speaker verification", IEEE Trans. Acoust. Speech Signal Process., Vol. 29, pp. 254-272.
37. S. Furui (1986), "Speaker independent isolated word recognizer using dynamic features of speech spectrum", IEEE Trans. Acoust. Speech Signal Process., Vol. 34, No. 1, pp. 52-59.
38. O. Ghitza and M.M. Sondhi (1993), "Hidden Markov-models with templates as non-stationary states: An application to speech recognition", Computer Speech and Language, Vol. 2, pp. 101-119.
39. H. Gish (1990), "A probabilistic approach to the understanding and training of neural network classifiers", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, pp. 1361-1364.
40. I.J. Good (1963), "Maximum entropy for hypothesis formulation, especially for multidimensional contingency tables", Ann. Math. Statist., Vol. 34, pp. 911-934.
41. G.G.R. Green (1976), Temporal aspects of audition, PhD Thesis, Oxford, UK.
42. S. Greenberg (1988), "The representation of speech in the auditory periphery", J. Phonetics, Vol. 16, pp. 1-151.
43. P.S. Gopalakrishnan, D. Kanecsky, A. Nada, D. Nahamoo and M.A. Picheny (1988), "Decoder selection based on cross-entropies", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., New York, NY, pp. 20-23.
44. W.D. Goldenthal (1994), Statistical trajectory models for phonetic recognition, PhD Thesis, MIT.
45. R. Haeb-Umbach, D. Geller and H. Ney (1994), "Improvements in connected digit recognition using linear discriminant analysis and mixture densities", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Adelaide, Australia, pp. II-239-242.
46. A. Hauenstein and E. Marschall (1995), "Methods for improved speech recognition over telephone line", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Detroit, MI. pp. 425-428.
47. B. Hanson and D. Wong (1984), "The harmonic magnitude suppression (HMS) technique for intelligibility enhancement in the presence in interfering speech", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., pp. 18.A.5.1-18.A.5.4.
48. H. Hermansky (1987), "An efficient speaker-independent automatic speech recognition by simulation of some properties of human auditory perception", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Dallas, TX, pp. 1159-1162.
49. H. Hermansky (1990), "Perceptual linear predictive (PLP) analysis of speech", J. Acoust. Soc. Amer., Vol. 87, No. 4, pp. 1738-1752.
50. H. Hermansky (1995), "Exploring temporal domain for robustness in speech recognition", Proc. 15th Internat. Congress on Acoustics, Trondheim, Norway, Vol. II., pp. 61-64.
51. H. Hermansky, H. Fujisaki and Y. Sato (1983), "Analysis and synthesis of speech based on spectral transform linear predictive method", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Boston, MA, pp. 777-780,
52. H. Hermansky and N. Morgan (1994), "'RASTA processing of speech", IEEE Trans. Speech Audio Process., Vol. 2, No. 4, pp. 578-589.
53. H. Hermansky, E. Wan and C. Avendano (1995), "Speech enhancement based on temporal processing", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Detroit, MI, pp. 405-408.
54. M.M. Hochberg, S.J. Renais, A.J. Robinson and G.D. Cook (1995), "Recent improvements to the ABBOT large vocabulary CSR system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Detroit, MI, pp. 69-72.
55. M. Hunt and C. Lefebvre (1989), "A comparison of several acoustic representations for speech recognition with degraded and undegraded speech", Internat. Conf. Acoust. Speech Signal Process., Glasgow, Scotland, pp. 262-265.
56. S. Itahashi and S. Yokoyama (1976). "Automatic formant extraction utilizing mel scale and equal loudness contour", Internat. Conf. Acoust. Speech Signal Process., Philadelphia, PA, pp. 310-313.
57. R.D.T. Janseen, M. Fanty and R.A. Cole (1991), "Speaker independent phonetic classification in continuous English letters", Proc, Internat. Joint Conf. on Neural Networks, Seattle, WA, pp. II-801-808.
58. F. Jelinek, L.R. Bahl and R.L. Mercer (1975), "Design of a linguistic statistical decoder for the recognition of continuous speech", IEEE Trans. Information Theory, Vol. IT-21, pp. 250-256.
59. F. Jelinek (1976), "Continuous speech recognition by statistical methods", IEEE Proc., Vol. 64, No. 4, pp. 532-556.
60. F. Jelinek, B. Merialdo, S. Roukos, and M. Strauss (1991), "A dynamic language model for speech recognition", Proc. DARPA Speech and Nautral Language Workshop, Pacific Grove, CA, pp. 293-295.
61. M.I. Jordan and R.A. Jacobs (1994), "Hierarchical mixtures of experts and the EM algorithm", Neural Computation, Vol. 6, pp. 181-214.
62. B.H. Juang and L.R. Rabiner (1985), "Mixture autoregressive hidden Markov models for speech signals", IEEE Trans. Acoust. Speech Signal Process., Vol. 33, No. 6, pp. 1404-14013.
63. T. Kamm, A.G. Andreou and J. Cohen (1995), "Vocal tract normalization in speech recognition: Compensation for systematic speaker variability", Proc. 15th Annual Speech Research Symposium, Johns Hopkins University, Baltimore, MI, pp. 175-179.
64. S. Katagiri, C.H. Lee and B.H. Juang (1991), "New discriminative training algorithms based on the generalized probabilistic descent method", in Proc. IEEE Workshop on Neural Networks for Signal Process., edited by B.H. Juang, S.Y. Kung and C.A. Kamm (Morgan Kauffman, Los Altos, CA), pp. 299-308.
65. D.H. Klatt (1982), "Speech processing strategies based on auditory models", in The Representation of Speech in the Peripheral Auditory System, ed. by R. Carlson and B. Granstrom (Elsevier - Biomedical Press, New York), pp. 181-202.
66. C-H. Lee, C-H. Lin and B-H. Juang (1991), "A study on speaker adaptation of the parameters of continuous density hidden Markov models", IEEE Trans. Signal Process., Vol. 39, No. 4, pp. 806-814.
67. E. Levin (1993), "Hidden control neural architecture modeling of nonlinear time varying systems and its applications", IEEE Trans. Neural Networks, Vol. 4, No. 1, pp. 109-116.
68. J.S. Lim (1979), "Spectral root homomorphic deconvolution system", IEEE Trans. Acoust. Speech Signal Process., Vol. 27, No. 3, pp. 223-233.
69. L.A. Liporace (1982), "Maximum likelihood estimation for multivariate observations of Markov sources", IEEE Trans. Information Theory, Vol. IT-28, No. 5, pp. 729-734.
70. D.M. Lubensky, A.O. Asadi and J.M. Naik (1994), "Connected digit recognition using connectionist probability estimators and mixture-Gaussian densities", Proc. Internat. Conf. on Spoken Language Processing, Yokohama, Japan.
71. S. Makino, T. Kawabata and K. Kido (1983), "Recognition of consonant based on the Perceptron model", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Boston, MA, pp. 738-741.
72. P. Mermelstein (1976), "Distance measures for speech recognition, psychological and instrumental", in Pattern Recognition and Artificial Intelligence, ed. by R.C.H. Chen (Academic Press, New York), pp. 374-388.
73. N. Morgan and H. Bourlard (1990), "Continuous speech recognition using multilayer perceptrons with hidden Markov models", IEEE Proc. Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, pp. 413-416.
74. N. Morgan and H. Bourlard (1995), "Neural networks for statistical recognition of continuous speech", Proc. IEEE, Vol. 83, No. 5, pp. 741-770.
75. N. Morgan, H. Bourlard, S. Greenberg and H. Hermansky (1995), "Stochastic perceptual models of speech", IEEE Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 397-400.
76. N. Morgan, S.-L. Wu and H. Bourlard (1995), "Digit recognition with stochastic perceptual models", Proc. Eurospeech'95, Madrid, Spain, pp. 771-774.
77. L. Neumayer and M. Weintraub (1994), "Probabilistic optimum filtering for robust speech recognition". IEEE Proc. Internat. Conf. Acoust. Speech Signal Process., Adelaide, Australia, pp. I-417-420.
78. M. Ostendorf, I. Bechwati and O. Kimball (1992), "Context modeling with the stochastic segment model", IEEE Proc. Internat. Conf. Acoust. Speech Signal Process., San Francisco, CA, pp. 389-392.
79. D.B. Paul, J.K. Baker and J.M. Baker (1991), "On the interaction between true source, training, and testing language models", IEEE Proc. internat. Conf. Acoust. Speech Signal Process., Toronto, Canada, pp. 569-572.
80. M. Pavel and H. Hermansky (1994), "Temporal masking in automatic speech recognition", J. Acoust. Soc. Amer., Vol. 95, No. 5, pp. 2876.
81. L.C.W. Pols, L.J.T. v.d. Kamp and R. Plomp (1969), "Perceptual and physical space of vowel sounds", J. Acoust. Soc. Amer., Vol. 46, pp. 458-467.
82. L.C.W. Pols (1971), "Real-time recognition of spoken words", IEEE Trans. Computers, Vol. 20(C), pp. 972-978.
83. A.B. Poritz (1982), "Linear predictive hidden Markov models and the speech signal", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Paris, France, pp. 1291-1294.
84. A.B. Poritz and A.G. Richter (1986), "On hidden Markov models in isolated word recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Tokyo, Japan, pp. 705-708.
85. J.E. Porter and S.F. Boll (1984), "Optimal estimators for spectral restoration of noisy speech", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., San Diego, CA, pp. 18.A.2.1.-18.A.2.4.
86. L.R. Rabiner (1989), "A tutorial on hidden Markov models and selected applications in speech recognition", Proc. IEEE, Vol. 77, No. 2, pp. 257-285.
87. S. Renals and M. Hochberg (1995), "Efficient search using posterior phone probability estimates", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Detroit, MI, pp. 596-599.
88. M.D. Richard and R.P. Lippmann (1991), "Neural network classifiers estimate Bayesian a posteriori probabilities", Neural Computation, Vol. 3, pp. 461-483.
89. T. Robinson, L. Almeida, J.M. Boite, H. Bourlard, F. Fallside, M. Hochberg, D. Kershaw, P. Kohn, Y. Konig, N. Morgan, J.P. Neto, S. Renals, M. Saerens and C. Wooters (1993), "A neural network based, speaker independent, large vocabulary, continuous speech recognition system: the Wernicke project", Proc. Eurospeech'93, Berlin, Germany, pp. 1941-1944.
90. T. Robinson and F. Fallside (1991), "A recurrent error propagation network speech recognition system", Computer Speech and Language, Vol. 5, pp. 259-274.
91. A.E. Rosenberg, C. Lee and F.K. Soong (1994), "Cepstral channel normalization techniques for HMM-based speaker verification", Proc. Internat. Conf. on Spoken Language Processing, Yokohama, Japan, pp. 1835-1838.
92. M.J. Russell, K.M. Ponting, S.M. Peeling, S.R. Browning, J.S. Bridle, R.K. Moore, I. Galiano and P. Howell (1990), "The ARM continuous speech recognition system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Albuquerque, NM, pp. 69-72.
93. R. Schwartz, S. Austin, F. Kubala, J. Makhoul, L. Nguyen, P. Placeway and G. Zavaliagkos (1992), "New uses of the N-best sentence hypotheses within the BYBLOS speech recognition system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., San Francisco, CA, pp. I-1.4-1.7.
94. S. Seneff (1985), "A joint synchrony/mean-rate model of auditory speech processing", J. Phonetics, Vol. 16, No. 1, pp.55-76.
95. E. Singer and R. Lippmann (1992), "A speech recognizer using radial basis function neural networks in an HMM framework", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., San Francisco, CA, pp. 629-632.
96. J.M. Steeneken and D.A. Van Leeuwen (1995), "Multilingual assessment of speaker independent large vocabulary speech-recognition systems: The SQALE project (speech recognition quality assessment for language engineering)", Proc. Eurospeech'95, Madrid, Spain, pp. 1271-1274.
97. S.S. Stevens (1957), "On the psychophysical law", Psychol. Rev., Vol. 64, No. 1, pp. 153-181.
98. J.C. Stevens and J.W. Hall (1966), "Brightness and loudness as functions of stimulus duration", Perception and Psychophysics, pp. 319-327.
99. T. Stockham, T. Cannon and R. Ingerbretsen (1975), "Blind deconvolution through digital signal processing", Proc. IEEE, Vol. 63, pp. 678-692.
100. C.C. Tappert and S.K. Das (1978), "Memory and time improvements in a dynamic programming algorithm for matching speech patterns", IEEE Trans. Acoust. Speech Signal Process., Vol. 26, pp. 583-586.
101. J. Tebelskis, A. Waibel, B. Petek and O. Schmidbauer (1991), "Continuous speech recognition using linked predictive neural networks", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Toronto, Canada, pp. 61-64.
102. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano and K. Lang (1988), "Phoneme recognition using time-delay neural networks", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., New York, NY, pp. 107-110.
103. C.J. Wellekens (1987), "Explicit time correlation in hidden Markov models for speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Dallas, TX, pp. 384-386.
104. E. Zwicker (1975), "Scaling", in Handbook of Sensory Physiology, ed. by Keidel and Neff (Springer, Berlin, Vol. 3), pp. 401-448.
105. V. Zue (1985), "The use of speech knowledge in automatic speech recognition", Proc. IEEE, Vol. 73, No. 11, pp. 1602-1615,
106. H. Bourlard, H. Hermansky and N. Morgan (1996), "Copernicus and the ASR challenge - Waiting for Kepler", Proc. ARPA Speech Recognition Workshop, Arden House, NY, 18-21 February 1996.