Signal Modeling Techniques in Speech Recognition

Proceedings of the IEEE

Volumn 81, Issue 9, 1993, Pages 1215-1247

  Picone, Joseph W ^a  

^a TEXAS INSTRUMENTS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CONSTRAINT THEORY; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; PARAMETER ESTIMATION; PROBABILITY; ROBUSTNESS (CONTROL SYSTEMS); SIGNAL PROCESSING; SPECTRUM ANALYSIS; STATISTICAL METHODS;

NETWORK SEARCHING; PERCEPTUAL MEANINGFUL PARAMETERS; SIGNAL MODELING TECHNIQUES; SIGNAL PARAMETERIZATION; SIMILARITY TRANSFORM TECHNIQUES; SPECTRAL SHAPING; SYNTACTIC CONSTRAINTS; TEMPORAL CORRELATION;

SPEECH RECOGNITION;

EID: 0027659197     PISSN: 00189219     EISSN: 15582256     Source Type: Journal    
DOI: 10.1109/5.237532     Document Type: Article

References (116)

1. D. S. Pallet, “Speech results on resource management task,” in Proc. February 1989 DARPA Speech and Natural Language Workshop. Philadelphia, PA: Morgan Kaufman Pub., Feb. 1989, pp. 18–24.
2. D. Paul, “The Lincoln robust continuous speech recognizer,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 556–559.
3. J. G. Wilpon, R. P. Mikkilineni, D. B. Roe, and S. Gokcen, “Speech recognition: From the laboratory to the real world,” AT&T Tech. J., vol. 69, no. 5, pp. 14–24, Oct. 1990.
4. J. G. Wilpon, D. M. DeMarco, and R. P. Mikkilineni, “Isolated word recognition over the DDD telephone network—Results of two extensive field trials,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (New York, Apr. 1988), pp. 55–57.
5. B. Wheatley and J. Picone, “Voice across America: Toward robust speaker independent speech recognition for telecommunications applications,” Digital Signal Processing: A Rev. J., vol. 1, no. 2, pp. 45–64, Apr. 1991.
6. J. Picone, “The demographics of speaker independent digit recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 105–108.
7. J. G. Wilpon, C. H. Lee, and L. R. Rabiner, “Improvements in connected digit recognition using higher order spectral and energy features,” in Proc. IEEE Int. Conf on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, May 1991), pp. 349–352.
8. T. Matsuoka and K. Shikano, “Robust HMM phoneme modeling for different speaking styles,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, May 1991), pp. 265–268.
9. Y. T. Lee, “Information-theoretic distortion measures for speech recognition: Theoretical considerations and experimental results,” IEEE Trans. Signal Processing, vol. 39, no. 2, pp. 330–335, Feb. 1991.
10. Y. T. Lee and D. Kahn, “Information-theoretic distortion measures for speech recognition: Theoretical considerations and experimental results,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 785–788.
11. S. Furui, “On the use of hierarchical spectral dynamics in speech recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 789–792.
12. D. Mansour and B. H. Juang, “A family of distortion measures based upon projection operation for robust speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, no. 11, pp. 1659–1671, Nov. 1989.
13. Y. Tohkura, “A weighted cepstral distance measure for speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-35, no. 10, pp. 1414–1422, Oct. 1987.
14. G. R. Doddington, “Phonetically sensitive discriminants for improved speech recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 556–559.
15. M. J. Hunt and C. Lefebvre, “A comparison of several acoustic representations for speech recognition with degraded and undegraded speech,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 262–265.
16. B. H. Juang, L. R. Rabiner, and J. G. Wilpon, “On the use of bandpass liftering in speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-35, no. 7, pp. 947–954, July 1987.
17. V. N. Gupta, M. Lennig, and P. Mermelstein, “Integration of acoustic information in a large vocabulary word recognizer,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Dallas, TX, Apr. 1987), pp. 697–700.
18. E. L. Bocchieri and G. R. Doddington, “Frame specific statistical features for speaker-independent speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, no. 4, pp. 755–764, Aug. 1986.
19. P. K. Rajasekaran, G. R. Doddington, and J. Picone, “Recognition of speech under stress and in noise,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Tokyo, Japan, Apr. 1986), pp. 733–736.
20. K. Shikano, “Evaluation of LPC spectral matching measures for phonetic unit recognition,” Tech. Memo CMU-CS-86-108, Computer Sci. Dept., Camegie-Mellon Univ., Pittsburgh. PA, Feb. 3, 1986.
21. S. Furui, “Speaker-independent isolated word recognition using dynamic features of the speech spectrum,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, no. 1, pp. 52–59, Feb. 1986.
22. J. Makhoul, S. Raucos, and H. Gish, “Vector quantization in speech coding,” in Proc. IEEE, vol. 73, no. 11, pp. 1551–1588, Nov. 1985.
23. N. Nocerino, F. K. Soong, L. R. Rabiner, and D. H. Klatt, “Comparative study of several distortion measures for speech recognition,” in Proc. IEEE Int. Conf on Acoustics, Speech, and SignalProcessing (Tampa, FL, Mar. 1985), pp. 25–28.
24. L. R. Rabiner, K. C. Pan, and F. K. Soong, “On the performance of isolated word speech recognizers using vector quantization and temporal energy contours,” AT&T Bell Lab. Tech. vol. J., 63, no. 7, pp. 1245–1260, Sept. 1984.
25. L. R. Rabiner, S. E. Levinson, M. M. Sondhi, “On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition,” Bell Syst. Tech. J., vol. 62, no. 4, pp. 1075–1105, Apr. 1983.
26. S. B. Davis and P. Mermelstein, “Comparison of parametric representations of monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-28, no. 4, pp. 357–366, Aug. 1980.
27. A. V. Oppenheim and R. W. Schafer, Digital Signal Processing. Englewood Cliffs, NJ, Prentice-Hall, 1975.
28. J. R. Deller, J. G. Proakis, and J. H. L. Hansen, Discrete Time Processing of Speech Signals. New York: MacMillan, 1993.
29. L. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
30. J. G. Proakis, Digital Communications, 2nd ed. New York: McGraw-Hill, 1989.
31. J. Market and A. H. Gray, Jr., Linear Prediction of Speech. New York: Springer-Verlag, 1980.
32. L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals. Englewood Cliffs, NJ: Prentice-Hall, 1978.
33. A. M. Noll, “Problems of speech recognition in mobile environments,” in Proc. Int. Conf on Spoken Language Processing(Kobe, Japan, Nov. 1990), pp. 1133–1136.
34. Y. Nakadai and N. Sugamura, “A speech recognition method for noise environments using dual inputs,” in Proc. Int. Conf. on Spoken Language Processing (Kobe, Japan, Nov. 1990), pp. 1141–1144.
35. S. Tamura, “An analysis of a noise reduction neural network,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 2001–2004.
36. J. L. Hieronymus, D. McKelvie, and F. R. Mclnnes, “Use of acoustic sentence level and lexical stress in HSMM speech recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (San Francisco, CA Mar. 1992), pp. 225–227.
37. T. Matsui and S. Furui, “A text-independent speaker recognition method robust against utterance variations,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 377–380.
38. W. Hess, Pitch Determination of Speech Signals. New York: Springer-Verlag, 1983.
39. P. Papamichalis, Practical Approaches to Speech Coding. Englewood Cliffs, NJ: Prentice-Hall, 1987.
40. B. Gold and L. R. Rabiner, “Parallel processing techniques for estimating pitch periods of speech in the time domain,” J. Acoust. Soc. America, vol. 46, pt. 2, no. 2, pp. 442–448, Aug. 1969.
41. R. S. Sukkar, J. L. LoCicero, and J. Picone, “Design and implementation of a parallel processing based pitch detector,” IEEE J. Selected Areas Commun., vol. 6, no. 2, pp. 441–451, Feb. 1988.
42. J. Campbell and T. E. Tremain, “Voiced/unvoiced classification of speech with applications to the U.S. Government LPC-10E algorithm” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing(Tokyo, Japan, Apr. 1986), pp. 473–476.
43. V. C. Welch, T. E. Tremain, and J. P. Campbell, Jr., “A comparison of U.S. Government standard voice coders,” in IEEE Military Communications Conf. Rec., Sept. 1989, pp. 269–273.
44. J. Picone, G. R. Doddington, and B. G. Secrest, “Robust pitch detection in a noisy telephone environment,” in Proc. IEEE Int. Conf on Acoustics, Speech, and Signal Processing (Dallas, TX, Apr. 1987), pp. 1442–1445.
45. A. M. Noll, “Cepstrum pitch determination,” J. Acoust. Soc. America, vol. 41, no. 2, pp. 293–309, Feb. 1967.
46. G. von Bkésy, Experiments in Hearing. New York: McGraw-Hill, 1960.
47. J. Picone, “Analytic signal processing,” Ph.D. dissertation, Illinois Institute of Technology, Chicago, Dec. 1983.
48. K. Ogata, Modern Control Engineering. Englewood Cliffs, NJ: Prentice-Hall, 1970.
49. J. O. Pickles, An Introduction to the Physiology of Hearing. New York: Academic Press, 1988.
50. A. R. M/o ller, Auditory Physiology, New York: Academic Press, 1983.
51. D. O’Shaughnessy, Speech Communication: Human and Machine. New York: Addison-Wesley, 1987.
52. E. Zwicker and E. Terhardt, “Analytical expressions for critical-band rate and critical bandwidth as a function of frequency,” J. Acoust. Soc. America, vol. 68, no. 5, pp. 1523–1525, Dec. 1980.
53. J. B. Allen, “Cochlear modeling,” IEEE ASSP Mag., vol. 3, no. 3, pp. 3–29, Sept. 1985.
54. S. Seneff, “A joint synchrony/mean-rate model of auditory speech processing,” J. Phonetics, vol. 16, no. 1, pp. 55–76, Jan. 1988.
55. O. E. Brigham, The Fast Fourier Transform. Englewood Cliffs, NJ: Prentice-Hall, 1974.
56. B. S. Atal and S. L. Hanauer, “Speech analysis and synthesis by linear prediction of the speech wave,” J. Acoust. Soc. America, vol. 50, no. 2, pp. 637–655, Mar. 1971.
57. S. L. Marple, Jr., Digital Spectral Analysis With Applications. Englewood Cliffs, NJ: Prentice-Hall, 1987.
58. V. R. Viswanathan and J. Makhoul, “Quantization properties of transmission parameters in linear predictive systems,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-23, no. 3, pp. 309–321, June 1975.
59. B. S. Atal, “Predictive coding of speech at low bit rates,” IEEE Trans. Commun., vol. COM-30, no. 4, pp. 600–614, Apr. 1982.
60. B. S. Atal and J. R. Remde, “A new model of LPC excitation for producing natural sounding speech at low bit rates,” in Proc. IEEE Int. Conf on Acoustics, Speech, and Signal Processing (Paris, France, 1982), pp. 614–617.
61. G. R. Doddington, J. Picone, and J. J. Godfrey, “The LPC trace as an HMM development tool,” J. Acoust. Soc. America, vol. 84, p. S1-561A, Fall 1988.
62. H. F. Silverman and N. R. Dixon, “A parametrically controlled spectral analysis system for speech,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-22, no. 5, pp. 362–381, Oct. 1974 (not the original reference by any means, but a good reference on digital computation of the spectrogram—original references on analog techniques date back to the 1940’s).
63. R. V. Churchill, J. W. Brown, and R. F. Verhey, Complex Variables and Applications. New York: McGraw-Hill, 1976.
64. B. S. Atal, “Linear prediction for speaker identification,” J. Acoust. Soc. America, vol. 55, no. 6, pp. 1304–1311, June 1974.
65. A. V. Oppenheim and D. H. Johnson, “Discrete representation of signals,” in Proc. IEEE, vol. 60, no. 6, pp. 681–691, June 1972.
66. K. F. Lee, Automatic Speech Recognition: The Development of the SPHINX System. Boston, MA: Kluwer, 1989.
67. J. G. Wilpon, C. H. Lee, and L. R. Rabiner, “Application of hidden Markov models for recognition of a limited set of words in unconstrained speech,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, 1989), pp. 254–257.
68. R. W. Hamming, Digital Filters, 2nd ed. Englewood, Cliffs, NJ: Prentice-Hall, 1989.
69. H. Ney, “Experiments on mixture-density phoneme modelling for the speaker-independent 1000-word speech recognition DARPA task,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 713–716.
70. D. Paul, “A speaker-stress resistant isolated word recognizer,” in Proc. IEEE Int Conf. on Acoustics, Speech, and Signal Processing (Dallas, TX, Apr. 1990), pp. 713–716.
71. B. H. Juang, L. R. Rabiner, and J. G. Wilpon, “On the use of bandpass liftering in speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-35, no. 7, pp. 947–954, July 1987.
72. K. Fukunaga, Introduction to Statistical Pattern Recognition. New York: Academic Press, 1972.
73. J. Picone, “Continuous speech recognition using hidden Markov models IEEE ASSP Mag., vol. 7, no. 3, pp. 26–41, July 1990.
74. L. R. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257–285, Feb. 1989.
75. W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vettering, Numerical Recipes in C: The Art of Scientific Programming. New York: Cambridge Univ. Press, 1988.
76. M. R. Anderberg, Cluster Analysis for Applications. New York: Academic Press, 1973.
77. Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. Commun., vol. COM-28, no. 1, pp. 84–95, Jan. 1980.
78. S. E. Levinson, L. R. Rabiner, A. E. Rosenberg, and J. G. Wilpon, “Interactive clustering techniques for selecting speaker-independent reference templates for isolated word recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-27, no. 2, pp. 134–141, Apr. 1979.
79. J. Picone and G. R. Doddington, “Low rate speech coding using contour quantization,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Dallas, TX, Apr. 1987), pp. 1652–1655.
80. A. Gersho, “On the structure of vector quantizers,” IEEE Trans. Informat., Theory, vol. IT-28, no. 2, pp. 157–166, Mar. 1982.
81. T. Kohonen, Self-Organization and Associative Memory, 3rd ed. New York: Springer-Verlag, 1989.
82. R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis. New York: Academic Press, 1973.
83. F. Itakura, “Minimum prediction residual principle applied to speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-23, no. 1, pp. 67–72, Feb. 1975.
84. B. Dautrich, L. R. Rabiner, and T. B. Martin, “On the effects of varying filter bank parameters on isolated word recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-31, no. 4, pp. 793–807, Aug. 1983.
85. J.Picone, “Duration in context clustering for speech recognition,” Speech Commun., vol. 9, no. 2, pp. 119—128, Apr. 1990.
86. K. Kita, T. Kawabata, and H. Saito, “HMM continuous speech recognition using predictive LR parsing,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 703–706.
87. A. Waibel, T. Hanazawa, G. Hintom, K. Shikano, and K. J. Lang, “Phoneme recognition using time-delay neural networks,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, no. 3, pp. 328–339, Mar. 1989.
88. Y. L. Chow, M. O. Dunham, O. A. Kimball, M. A. Krasner, G. F. Kubala, J. Makhoul, P. J. Price, S. Roucos, and R. M. Schwartz, “BYBLOS: The BBN continuous speech recognition system,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Dallas, TX, Apr. 1987), pp. 89–92.
89. F. Kubala, M. Feng, J. Makhoul, and R. Schwartz, “Speaker adaptation from limited training in the BBN BYBLOS speech recognition system,” in Proc. DARPA Speech and Natural Language Workshop. Palo Alto, CA: Morgan Kaufmann Pub., Feb. 1989, pp. 100–105.
90. M. M. Hochberg, L. T. Niles, J. T. Foote, and H. F. Silverman, “Hidden Markov model/neural network training techniques for connected alphadigit speech recognition”, in Proc. IEEE Int.Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 109–112.
91. T. D. Harrison and F. Fallside, “A connectionist model for phoneme recognition in continuous speech,” in Proc. IEEE Int.Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 417–420.
92. P. Haffner, M. Franzini, and A. Waibel, “Integrating time alignment and neural networks for high performance continuous speech recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr.1991), pp.105–109.
93. L. Fissore, P. Laface, and G. Micca, “Comparison of discrete and continuous HMMs in a CSR task over the telephone,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 253–256.
94. L. Fissore, P. Laface, G. Micca, and R. Pieraccini, “Lexical access to large vocabularies for speech recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, no. 8, pp.1197–1213, Aug. 1989.
95. S. Kimura, “100,000-word recognition using acoustic-segment networks,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990). pp. 61–64.
96. A. Averbuch, L. Bahl, R. Bakis, P. Brown, A. Cole, G.Daggett, S. Das, K. Davies, S. De Gennaro, P. de Souza, E. Epstein, D. Fraleigh, F. Jelinek, S. Katz, B. Lewis, R. Mercer, A. Nadas, D. Nahamoo, M. Picheny, G. Shichman, and P. Spinelli, “An IBM-PC based large-vocabulary isolatedutterance speech recognizer,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Tokyo, Japan, Apr. 1986), pp. 53–56.
97. F. Jelinek, “The development of an experimental discrete dictation recognizer,” Proc. IEEE, vol. 73, no. 11, pp. 1616–1624, Nov. 1985.
98. L. Deng, V. Gupta, M. Lennig, P. Kenny, and P. Mermelstein, “Acoustic recognition component of an 86,000-word speech recognizer,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 741–784.
99. J. Koo, C. K. Un, H. S. Lee, H. R. Kim, and M. W. Koo, “A recognition time reduction algorithm for large-vocabulary speech recognition,” in Proc. Int. Conf. on Spoken Language Processing (Kobe, Japan, Nov. 1990), pp. 253–256.
100. V. Zue, J. Glass, M. Phillips, and S. Seneff, “Acoustic segmentation and phonetic classification in the SUMMIT system,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, May 1989), pp. 389–392.
101. S. Mizuta and K. Kakajima, “An optimal discriminative training method for continuous mixture density HMMs,” inProc. Int. Conf. on Spoken Language Processing (Kobe, Japan, Nov.1990), pp.245–248.
102. K. Yoshida, T. Watanabe, and S. Koga, “Large vocabulary word recognition based on demisyllable hidden Markov model using small amount of training data,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, 1989), pp. 1–4.
103. D. Lubensky, “Word recognition using neural nets, multi-state Gaussian and K-nearest neighbor classifiers,” inProc. IEEE Int.Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 141–144.
104. S. Matsunaga, S. Sagayama, S. Homma, and S. Furui, “A continuous speech recognition system based on a two-level grammar approach,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp.589–592.
105. T. Matsuoka and K. Shikano, “Robust HMM phoneme modeling for different speaking styles,” in Proc. IEEE Int. Conf.on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 265–268.
106. Y. Zhao and H. Wakita, “Experiments with a speakerindependent continuous speech recognition system onthe TIMIT database,” in Proc. Int. Conf. on Spoken Language Processing (Kobe, Japan, Nov. 1990), pp. 697–700.
107. V. Steinbiss, A. Noll, A. Paeseler, H. Ney, H. Bergmann, C.Dugast, H. H. Hamer, H. Piotrowski, H. Tomaschewski, and A. Zielinski, “A 10,000-word continuous speech recognition system,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM, Apr. 1990), pp. 57–60.
108. M. J. Russel, K. M. Ponting, S. M. Peeling, S. R. Browning, J.S. Bridle, R. K. Moore, I. Galiano, and P. Howell, “The ARM continuous speech recognition system,” inProc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (AI buquerque, NM, Apr. 1990), pp. 69–72.
109. M. Weintraub, H. Murveit, M. Cohen, P. Price, J. Bemstein, G.Baldwin, and D. Bell, “Linguistic constraints inhidden Markov model based speech recognition,” inProc.IEEE Inf. Conf. on Acoustics, Speech, and Signal Processing (Glasgow, Scotland, 1989), pp. 699–702.
110. H. Murveit and M. Weintraub, “1000-word speaker-independent continuous-speech recognition using hidden Markovmodels,” in Proc. IEEE Int. Conf. on Acoustics, Speech, andSignal Processing (New York, Apr. 1988), pp. 115–118.
111. W. S. Meisel, M. T. Anikst, S. S. Pirzadeh, J. E. Schumacher, M. C. Soares, and D. J. Trawick, “The SSI large vocabulary speaker-independent continuous speech recognition system,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Ont., Canada, Apr. 1991), pp. 273–276.
112. S. Makino, A. Ito, M. Endo, and K. Kido, “A Japanese text dictation system based on phoneme recognition and a dependency grammar,” in Proc. IEEE Int. Conf. on Acoustics, Speech. and Simal Processing (Toronto. Ont., Canada. Apr.1989), pp. 699–702.
113. K. Shirai, N. Hosaka, E. Kitagawa, and T. Endou, “Speaker adaptable phoneme recognition selecting reliable acoustic features based on mutual information,” in Proc. Int. Conf. on Spoken Language Processing (Kobe, Japan, Nov. 1990). pp.353–356.
114. H. M. Meng and V. W. Zue, “A comparative study of acoustic representations of speech for vowel classificationusing multi-layer preceptrons,” in Proc. Int. Conf.SpokenLanguage Processing (Kobe, Japan, Nov. 1990), pp. 1053–1056.
115. R. G. Leonard, “A database for speaker-independent digit recognition,” in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (San Diego, CA, Apr. 1984).pp.42.11.1–42.11.4.
116. H. Hermansky and N. Morgan, “Towards handling the acoustic environment in spoken language processing,” in Proc. Int. Conf.on Spoken Language Processing (Banff, Alta., Canada, Oct.1992), pp. 85–88.