Title :
A*-admissible heuristics for rapid lexical access
Author :
Kenny, Patrick ; Hollan, Rene ; Gupta, Vishwa N. ; Lennig, Matthew ; Mermelstein, P. ; O´Shaughnessy, Douglas
Author_Institution :
INRS Telecommun., Montreal, Que., Canada
fDate :
1/1/1993 12:00:00 AM
Abstract :
A new class of A* algorithms for Viterbi phonetic decoding subject to lexical constraints is presented. This type of algorithm can be made to run substantially faster than the Viterbi algorithm in an isolated word recognizer having a vocabulary of 1600 words. In addition, multiple recognition hypotheses can be generated on demand and the search can be constrained in respect conditions on phone durations in such a way that computational requirements are substantially reduced. Results are presented on a 60000-word recognition task
Keywords :
dynamic programming; speech recognition; A* algorithms; A*-admissible heuristics; Viterbi phonetic decoding; dynamic programming algorithms; isolated word recognizer; lexical access; lexical constraints; multiple recognition hypotheses; phone durations; search; speech recognition; vocabulary; Councils; Decoding; Hidden Markov models; Out of order; Speech recognition; Telecommunication computing; Topology; Viterbi algorithm; Vocabulary;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on