DocumentCode
294638
Title
A tree search strategy for large-vocabulary continuous speech recognition
Author
Gopalakrishnan, P.S. ; Bahl, L.R. ; Mercer, R.L.
Author_Institution
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Volume
1
fYear
1995
fDate
9-12 May 1995
Firstpage
572
Abstract
We describe a tree search strategy, called the Envelope Search, which is a time-asynchronous search scheme that combines aspects of the A* heuristic search algorithm with those of the time-synchronous Viterbi search algorithm. This search technique is used in the large-vocabulary continuous speech recognition system developed at the IBM Research Center
Keywords
maximum likelihood estimation; natural languages; speech processing; speech recognition; tree searching; A* heuristic search algorithm; Envelope Search; IBM Research Center; language models; large-vocabulary continuous speech recognition; time-asynchronous search; time-synchronous Viterbi search algorithm; tree search; Cost function; Iterative decoding; Speech recognition; Terminology; Viterbi algorithm; Vocabulary; Yttrium;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location
Detroit, MI
ISSN
1520-6149
Print_ISBN
0-7803-2431-5
Type
conf
DOI
10.1109/ICASSP.1995.479662
Filename
479662
Link To Document