An A* algorithm for very large vocabulary continuous speech recognition

Authors:
P. Kenny;R. Hollan;G. Boulianne;H. Garudadri;M. Lennig;D. O'Shaughnessy
Affiliations:
INRS-Télécommunications, Montreal, Quebec, Canada;INRS-Télécommunications, Montreal, Quebec, Canada;INRS-Télécommunications, Montreal, Quebec, Canada;INRS-Télécommunications, Montreal, Quebec, Canada;INRS-Télécommunications, Montreal, Quebec, Canada;INRS-Télécommunications, Montreal, Quebec, Canada
Venue:
HLT '91 Proceedings of the workshop on Speech and Natural Language
Year:
1992

Citing 2
Cited 1

Principles of artificial intelligence

Principles of artificial intelligence
An 86,000-word recognizer based on phonemic models

HLT '90 Proceedings of the workshop on Speech and Natural Language

A new fast match for very large vocabulary continuous speech recognition

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new search algorithm for very large vocabulary continuous speech recognition. Continuous speech recognition with this algorithm is only about 10 times more computationally expensive than isolated word recognition. We report preliminary recognition results obtained by testing our recognizer on "books on tape" using a 60,000 word dictionary.