Start-synchronous search for large vocabulary continuous speech recognition

Start-synchronous search for large vocabulary continuous speech recognition

Cached

Download Links

[www.ee.columbia.edu]

by Steve Renals , Michael M. Hochberg

Venue:	IEEE Trans. Speech and Audio Processing
Citations:	17 - 9 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Start-synchronous search for large vocabulary continuous speech recognition	INFERENCE
AUTHOR NAME	Steve Renals	SVM HeaderParse 0.2
AUTHOR NAME	Michael M. Hochberg	SVM HeaderParse 0.2
ABSTRACT	Abstract — In this paper, we present a novel, efficient search strategy for large vocabulary continuous speech recognition. The search algorithm, based on a stack decoder framework, utilizes phone-level posterior probability estimates (produced by a connectionist/hidden Markov model acoustic model) as a basis for phone deactivation pruning—a highly efficient method of reducing the required computation. The single-pass algorithm is naturally factored into the time-asynchronous processing of the word sequence and the time-synchronous processing of the hidden Markov model state sequence. This enables the search to be decoupled from the language model while still maintaining the computational benefits of time-synchronous processing. The incorporation of the language model in the search is discussed and computationally cheap approximations to the full language model are introduced. Experiments were performed on the North American Business News task using a 60 000 word vocabulary and a trigram language model. Results indicate that the computational cost of the search may be reduced by more than a factor of 40 with a relative search error of less than 2 % using the techniques discussed in the paper. Index Terms — Hidden Markov model, large vocabulary continuous speech recognition, phone deactivation pruning, search, stack decoding. I.	SVM HeaderParse 0.2
VENUE	IEEE Trans. Speech and Audio Processing	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	37 found	ParsCit 1.0