Title :
A fast approximate acoustic match for large vocabulary speech recognition
Author :
Bahl, Lalit R. ; De Gennaro, Steven V. ; Gopalakrishnan, P.S. ; Mercer, Robert L.
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
fDate :
1/1/1993 12:00:00 AM
Abstract :
In a large vocabulary speech recognition system using hidden Markov models, calculating the likelihood of an acoustic signal segment for all the words in the vocabulary involves a large amount of computation. In order to run in real time on a modest amount of hardware, it is important that these detailed acoustic likelihood computations be performed only on words which have a reasonable probability of being the word that was spoken. The authors describe a scheme for rapidly obtaining an approximate acoustic match for all the words in the vocabulary in such a way as to ensure that the correct word is, with high probability, one of a small number of words examined in detail. Using fast search methods, they obtain a matching algorithm that is about a hundred times faster than doing a detailed acoustic likelihood computation on all the words in the IBM Office Correspondence isolated word dictation task, which has a vocabulary of 20000 words. Experimental results showing the effectiveness of such a fast match for a number of talkers are given
Keywords :
acoustic signal processing; dictation; hidden Markov models; search problems; speech recognition; IBM Office Correspondence; acoustic likelihood computations; acoustic signal segment; approximate acoustic match; fast search methods; hidden Markov models; isolated word dictation task; large vocabulary speech recognition; matching algorithm; Acoustics; Arithmetic; Hardware; Hidden Markov models; Iterative decoding; Out of order; Search methods; Speech processing; Speech recognition; Vocabulary;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on