Abstract
This paper describes an algorithm for performing fast selection of word candidates to speed up the decoding of continuous speech. Interacting with word transitions, it fits very well into standard Viterbi decoding. The main features are: a tree-organization of the lexicon, coarse models deduced from the detailed ones, a selection rule compatible with unknown word boundaries, an efficient DP implementation. Various applications show a global reduction of the search cost by a factor 5 to 10 depending on the lexicon size, the error rate being increased by less than 1%.
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
Aubert X.L., “Fast Look-Ahead Pruning Strategies in Continuous Speech Recognition”, Proc. ICASSP, Glasgow, pp. 659–662, 1989.
Bahl L., De Gennaro S., Gopalakrishnan P. & Mercer R., “A Fast Approximate Acoustic Match for Large Vocabulary Speech Recognition”, Proc. Eurospeech, Paris, pp.156–158, 1989.
Ney H., Mergel D., Noll A. & Paeseler A., “A Data-Driven Organization of the Dynamic Programming Beam Search for Continuous Speech Recognition”, Proc. ICASSP, Dallas, 1987.
Ney H., Noll A., “Phoneme Modelling using Continuous Mixture Densities”, Proc. ICASSP, New-York, pp. 437–440, 1988.
Steinbiss V., Noll A., Paeseler A., Ney H. et al., “A 10,000-word Continuous Speech Recognition System”, Proc. ICASSP, Albuquerque, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aubert, X.L. (1992). A Fast Lexical Selection Strategy for Large Vocabulary Continuous Speech Recognition. In: Laface, P., De Mori, R. (eds) Speech Recognition and Understanding. NATO ASI Series, vol 75. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76626-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-76626-8_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76628-2
Online ISBN: 978-3-642-76626-8
eBook Packages: Springer Book Archive