Abstract
A method for deriving equivalence classes for lexical access in speech recognition is considered, which automatically derives equivalence classes from training data using unsupervised learning and the Minimum Message Length Criterion. These classes model insertions, deletions and substitutions in an input phoneme string due to mis-recognition and mis-pronunciation, and allow unlikely word candidates to be eliminated quickly. This in turn allows a more detailed examination of the remaining candidates to be carried out efficiently.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Altman, G. and Carter, D., Lexical stress and lexical discriminability: Stressed syllables are more informative, but why? Computer Speech and Language 3, 265–275, 1989.
Chen, F.R., Lexical access and verification in a broad phonetic approach to continuous digit recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 21.7.1–21.7.4, 1986.
Fisher, W.M., Doddington, M., George, R., and Goudie-Marshall, K.M., The DARPA speech recognition database: Specifications and status. In Proceedings of the DARPA Speech Recognition Workshop, Report No. SAIC-86/1546, February 1986.
Fissore, L., Micca, G., and Pieraccini, R., Strategies for lexical access to very large vocabularies. Speech Communication 7, 355–366, 1988.
Huttenlocher, D.P. and Zue, V.W., A model for lexical access from partial phonetic information. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 26.4.1–26.4.4, 1984.
Patrick, J.D., Snob: A program for discriminating between classes. Technical Report 91/151, Monash University, March 1991.
Pisoni, D.B., Nusbaum, H.C., Luce, P.A., and Slowiaczek, L.M., Speech perception, word recognition and the structure of the lexicon. Speech Communication 4, 75–95, 1985.
Rudnicky, A.I., An unanchored matching algorithm for lexical access. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 469–472, 1988.
Rudnicky, A.I., Baumeister, L.K., DeGraaf, K.H., and Lehmann, E., The lexical access component of the CMU continuous speech recognition system. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 10.5.1–10.5.4, 1987.
Thomas, I.E., Zukerman, I., and Raskutti, B., Accounting for pronunciation of phonemes in corpora. In Proceedings of the Second Conference of the Pacific Association of Computational Linguistics, forthcoming.
Wallace, C.S. and Boulton, D.M., An information measure for classification. Computer Journal 11, 185–194, 1968.
Wallace, C.S. and Dowe, D.L., Intrinsic classification by MML — the Snob program. In Zhang, C., Debenham, J., and Lukose, D. (Eds.), Proceedings of the 7th Australian Joint Conference on Artificial Intelligence, 37–44, World Scientific, Singapore, 1994.
Wallace, C.S. and Freeman, P.R., Estimation and inference by compact coding. Journal of the Royal Statistical Society (Series B) 49, 240–252, 1987.
Withgott, M.M. and Chen, F.R., Computational Models of American Speech. Center for the Study of Language and Information, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thomas, I., Zukerman, I., Oliver, J., Raskutti, B. (1996). Lexical access using minimum message length encoding. In: Foo, N., Goebel, R. (eds) PRICAI'96: Topics in Artificial Intelligence. PRICAI 1996. Lecture Notes in Computer Science, vol 1114. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61532-6_20
Download citation
DOI: https://doi.org/10.1007/3-540-61532-6_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61532-3
Online ISBN: 978-3-540-68729-0
eBook Packages: Springer Book Archive