Hybrid grammar-bigram speech recognition system with first-order dependence model

Authors:
J. H. Wright;G. J. F. Jones;E. N. Wrigley
Affiliations:
Centre for Communications Research, University of Bristol, Bristol, UK;Centre for Communications Research, University of Bristol, Bristol, UK;Centre for Communications Research, University of Bristol, Bristol, UK
Venue:
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Year:
1992

Citing 3
Cited 0

Generalized L.R. Parsing

Generalized L.R. Parsing
Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
Incorporating LR parsing into SPHINX

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

An experimental PC-based isolated-word sentence recogniser with two competing language models is described. A probabilistic grammar acts as the main language model and gives the best performance for sentences within its scope, and a bigram model serves as backup for the exceptions. Automatic language model selection is based on probability. Context-free parse tree probabilities are products of probabilities of the rules invoked. This context-freeness is unrealistic, and a method for imposing limited context dependence on the rules is described, using first-order conditional probabilities controlled by mutual information. The method has the advantage of being data-driven, based on measured joint distributions of pairs of symbols.