Abstract
The performance of a large vocabulary speech recognition system is critically tied to the quality of the acoustic prototypes that are established in the relevant feature space(s). This is especially true in continuous speech and/or for speaker-independent tasks, where pronunciation variability is the greatest. In this chapter, we will discuss a number of clustering techniques which can be used to derive high quality acoustic prototypes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
L.R. Bahl, F. Jelinek, and R.L. Mercer, “A Maximum Likelihood Approach to Continuous Speech Recognition,” IEEE Trans. Pattern Anal. Mach. Intel., Vol. PAMI-5, No. 2, pp. 179–190, March 1983.
L.R. Bahl, P.F. Brown, P.V. de Souza, R.L. Mercer, and M.A. Picheny, “Automatic Construction of Acoustic Markov Models for Words,” in Proc. 1987 Int. Symp. on Signal Proc. and Its Applic, Brisbane, Australia, pp. 565–569, May 1987.
L.R. Bahl, P.F. Brown, P.V. de Souza, R.L. Mercer, and M.A. Picheny, “Acoustic Markov Models Used in the Tangora Speech Recognition System,” in Proc. 1988 Int. Conf. Acoust., Speech, Signal Processing, New York, NY, pp. 497–500, April 1988.
L.R. Bahl, R. Bakis, J.R. Bellegarda, P.F. Brown, D. Burshtein, S.K. Das, P.V. de Souza, P.S. Gopalakrishnan, F. Jelinek, D. Kanevsky, R.L. Mercer, A.J. Nadas, D. Nahamoo, and M.A. Picheny, “Large Vocabulary Natural Language Continuous Speech Recognition,” in Proc. 1989 Int. Conf. Acoust., Speech, Signal Processing, Glasgow, Scotland, pp. 465–467, May 1989.
L.R. Bahl, J.R. Bellegarda, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, and M.A. Picheny, “A New Class of Fenonic Markov Word Models for Large Vocabulary Continuous Speech Recognition,” in Proc. 1991 Int. Conf. Acoust., Speech, Signal Processing, Toronto, Canada, pp. 177–180, May 1991.
L.R. Bahl, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, M.A. Picheny, “Decision Trees for Phonological Rules in Continuous Speech,” in Proc. 1991 Int. Conf. Acoust., Speech, Signal Processing, Toronto, Canada, pp. 185–188, May 1991.
L.R. Bahl, P.V. de Souza, P.S. Gopalakrishnan, and M.A. Picheny, “Context-Dependent Vector Quantization for Continuous Speech Recognition,” in Proc. 1993 Int. Conf. Acoust., Speech, Signal Processing, Minneapolis, MN, pp. I632-I635, May 1993.
L.R. Bahl, J.R. Bellegarda, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, and M.A. Picheny, “Multonic Markov Word Models for Large Vocabulary Continuous Speech Recognition,” IEEE Trans. Speech Audio Processing, Vol. SAP-1, No. 3, pp. 334–344, July 1993.
L. Bahl, P. de Souza, P. S. Gopalakrishnan, D. Nahamoo, M. Picheny, “Robust Methods for Using Context Dependent Features and Models in a Continuous Speech Recognizer,”, in Proc. 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, April 1994.
J.R. Bellegarda and D. Nahamoo, “Tied Mixture Continuous Parameter Modeling for Speech Recognition,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. ASSP-38, No. 12, pp. 2033–2045, December 1990.
J.R. Bellegarda P.V. de Souza, A.J. Nadas, D. Nahamoo, M.A. Picheny, and L.R. Bahl, “Robust Speaker Adaptation Using a Piecewise Linear Acoustic Mapping,” in Proc. 1992 Int. Conf Acoust., Speech, Signal Processing, San Francisco, CA, pp. I445-I448, March 1992.
J.R. Bellegarda, P.V. de Souza, D. Nahamoo, M.A. Picheny, and L.R. Bahl, “A Supervised Approach to the Construction of Context-Sensitive Acoustic Prototypes,” in Proceedings 1993 IEEE Int. Conf. Acoust, Speech, Signal Processing, Minneapolis, Minnesota, pp. II644-II647, April 1993.
J.R. Bellegarda, P.V. de Souza, A.J. Nadas, D. Nahamoo, M.A. Picheny, and L.R. Bahl, “The Metamorphic Algorithm: A Speaker Mapping Approach to Data Augmentation,” IEEE Trans. Speech Audio Processing, Vol. SAP-2, No. 3, pp. 413–420, July 1994.
P.F. Brown, The Acoustic Modeling Problem in Automatic Speech Recognition, Ph.D. Thesis, Carnegie Mellon University, Pittsburgh, PA, 1987.
P.A. Chou, Applications of Information Theory to Pattern Recognition and the Design of Decision Trees and Trellises, Ph.D. Thesis, Stanford University, Stanford, CA, 1988.
J.R. Cohen, “Application of an Auditory Model to Speech Recognition,” J. Acoust Soc. Am., Vol. 85, No. 6, pp. 2623–2629, June 1989.
T. Dalenius, “The Problem of Optimum Stratification,” Skandinavisk Ak-tuarietidskrift, Vol. 34, pp. 133–148, 1951.
V. Digalakis and H. Murveit, “Genones: Optimizing the Degree of Tying in a Large Vocabulary HMM-based Speech Recognizer,”, in Proc. 1994 Int. Conf Acoust, Speech, Signal Processing, Adelaide, Australia, April 1994.
G. Fant, Speech Sound and Features, Cambridge, MA: MIT Press, 1973.
J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, and N.L. Dahlgreen, “The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CDROM,” NIST order number PB91–100354.
J.A. Hartigan, Clustering Algorithms, New York, NY: J. Wiley, 1975.
X.D. Huang, “Phoneme Classification Using Semi-Continuous Hidden Markov Models,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. ASSP-40, No. 5, pp. 1062–1067, May 1992.
M.-Y. Hwang and X. Huang, “Subphonetic Modeling with Markov State Models,” in Proc. 1992 Int. Conf. Acoust, Speech, Signal Processing, San Francisco, CA, pp. 133–136, March 1992.
M.-Y. Hwang, X. Huang, and F. Alleva, “Predicting Unseen Triphones with Senones,” in Proc. 1993 Int. Conf Acoust, Speech, Signal Processing, Minneapolis, MN, pp. II311-II314, March 1992.
F. Jelinek, “The Development of an Experimental Discrete Dictation Recognizer,” Proc. IEEE, Vol. 73, No. 11, pp. 1616–1624, November 1985.
C.-H. Lee, “Acoustic Modeling of Subword Units for Speech Recognition”, in Proc. 1990 Int. Conf. Acoust., Speech, Signal Processing, Albuquerque, NM, pp. 721–724, April 1990.
C.-H. Lee, L.R. Rabiner, R. Pieraccini, and J.G. Wilpon, “Acoustic Modeling for Large Vocabulary Speech Recognition”, Computer Speech and Language, Vol. 4, No. 2, pp. 127–165, April 1990.
K.F. Lee, Automatic Speech Recognition: The Development of the SPHINX System, Boston, MA: Kluwer Academic Publishers, 1989.
K.F. Lee, “Context-Dependent Phonetic Hidden Markov Models for Continuous Speech Recognition”, IEEE Trans. Acoust., Speech, Signal Processing, Vol. 38, No. 4, pp. 599–609, April 1990.
K.F. Lee, S. Hayamizu, H.W. Hon, C. Huang, J. Schwartz, and R. Weide, “Allophone Clustering for Continuous Speech Recognition”, in Proc. 1990 Int. Conf. Acoust., Speech, Signal Processing, Albuquerque, NM, pp. 749–752, April 1990.
A. Nadas, R.L. Mercer, L.R. Bahl, R. Bakis, P.S. Cohen, A.G. Cole, F. Jelinek, and B.L. Lewis, “Continuous Speech Recognition with Automatically Selected Prototypes Using Either Bootstrapping or Clustering,” in Proc. 1981 Int. Conf. Acoust., Speech, Signal Processing, Atlanta, GA, pp. 1153–1156, April 1981.
A. Nádas, D. Nahamoo, and M.A. Picheny, “Speech Recognition Using Noise-Adaptive Prototypes,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. 37, No. 10, pp. 1495–1503, October 1989.
D. Nahamoo and L.R. Bahl, “Tree-Based Approaches to Speech and Language Modeling”, Chapter 7 of this book.
M. Nishimura, “HMM-Based Speech Recognition Using Dynamic Spectral Feature,” in Proc. 1989 Int. Conf Acoust, Speech, Signal Processing, Glasgow, UK, pp. 298–301, May 1989.
D.S. Pallett, J.G. Fiscus, W.M. Fisher, J.S. Garofolo, B.A. Lund, and M.A. Pryzbocki, “1993 Benchmark Tests for the ARPA Spoken Language Program,” in Proc. ARPA Speech and Natural Language Workshop, Morgan Kaufmann Publishers, pp. 51–73, March 1994.
M. Phillips, J. Glass, V. Zue, “Modelling Context Dependency in Acoustic-Phonetic and Lexical Representations”, Proceedings of the DARPA Speech and Natural Language Workshop, Pacific Grove, CA, pp. 71–76, February 1991.
M.A. Picheny and S. Roukos, “Large Vocabulary Isolated Speech Dictation - The IBM Tangora System”, Chapter 14 of this book.
L.R. Rabiner, B.H. Juang, S.E. Levinson, and M.M. Sondhi, “Recognition of Isolated Digits Using Hidden Markov Models with Continuous Mixture Densities”, AT&T Tech. J., Vol. 64, No. 6, pp. 1211–1233, 1985.
L.R. Rabiner et al., “An Overview of Automatic Speech Recognition”, Chapter 1 of this book.
S. Sagayama and S. Homma, “An Allophone Clustering Technique Applied to Large Vocabulary Word Speech Recognition”, Proc. 1991 IEEE Int. Conf. Acoust., Speech, Signal Processing, Toronto, Canada, May 1991.
R. Schwartz, Y. Chow, O. Kimball, S. Roucos, M. Krasner, and J. Makhoul, “Context-Dependent Modeling for Acoustic-Phonetic Recognition of Continuous Speech,” in Proc. 1985 Int. Conf. Acoust., Speech, Signal Processing, Tampa, FL, April 1985.
P.C. Woodland, J.J. Odell, V. Valtchev, and S.J. Young, “Large Vocabulary Continuous Speech Recognition Using HTK,” in Proc. 1994 IEEE Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, April 1994.
S.J. Young and P.C. Woodland, “The Use of State Tying in Continuous Speech Recognition,” in Proc. EUROSPEECim, Berlin, Germany, September 1993.
Y. Zhao, “A Speaker-Independent Continuous Speech Recognition System Using Continuous Mixture Gaussian Density HMM of Phoneme-Sized Units,” IEEE Trans. Speech Audio Processing, Vol. SAP-1, No. 3, pp. 345–361, July 1994.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Kluwer Academic Publishers
About this chapter
Cite this chapter
Bellegarda, J.R. (1996). Context-Dependent Vector Clustering for Speech Recognition. In: Lee, CH., Soong, F.K., Paliwal, K.K. (eds) Automatic Speech and Speaker Recognition. The Kluwer International Series in Engineering and Computer Science, vol 355. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1367-0_6
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1367-0_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8590-8
Online ISBN: 978-1-4613-1367-0
eBook Packages: Springer Book Archive