DocumentCode
2228668
Title
New developments in the INRS continuous speech recognition system
Author
Li, Z. ; Héon, M. ; O´Shaughnessy, D.
Author_Institution
INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
Volume
1
fYear
1996
fDate
3-6 Oct 1996
Firstpage
2
Abstract
New techniques are developed for the second pass search in our large vocabulary continuous speech recognition system. The merging of recognition hypotheses is proposed in order to linearize the exponential growth of the tree structure in the depth first search. Branching ordering of the first pass word graph and pruning at both word and phone levels are used to further speed up the search. The algorithm has been shown to be effective on the speaker-independent WSJ task
Keywords
merging; natural language interfaces; speech recognition; tree searching; vocabulary; INRS; branching ordering; continuous speech recognition system; depth first search; exponential growth; first pass word graph; large vocabulary; new developments; phone level; pruning; recognition hypotheses; second pass search; speaker-independent WSJ task; tree structure; word level; Business; Merging; Natural languages; Speech recognition; Tree data structures; Tree graphs; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location
Philadelphia, PA
Print_ISBN
0-7803-3555-4
Type
conf
DOI
10.1109/ICSLP.1996.606915
Filename
606915
Link To Document