Efficient grammar processing for a spoken language translation system

Authors:
David B. Roe;Fernando C. N. Pereira;Richard W. Sproat;Michael D. Riley;Pedro J. Moreno;Alejandro Macarrón
Affiliations:
AT&T Bell Laboratories, Murray Hill, New Jersey;AT&T Bell Laboratories, Murray Hill, New Jersey;AT&T Bell Laboratories, Murray Hill, New Jersey;AT&T Bell Laboratories, Murray Hill, New Jersey;Carnegie Mellon University, Department of Electrical and Computer Engineering and Telefónica, I+D;Telefónica, I+D
Venue:
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Year:
1992

Citing 5
Cited 0

\Phi DM-Dialog: An Experimental Speech-to-Speech Dialog Translation System

Computer
A spoken language translator for restricted-domain context-free languages

Speech Communication - Eurospeech '91
An efficient context-free parsing algorithm

Communications of the ACM
Finite-state approximation of phrase structure grammars

ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

A problem with many speech understanding systems is that grammars that are more suitable for representing the relation between sentences and their meanings, such as context free grammars (CFGs) and augmented phrase structure grammars (APSGs), are computationally very demanding. On the other hand, finite state grammars are efficient, but cannot represent directly the sentence-meaning relation. We describe how speech recognition and language analysis can be tightly coupled by developing an APSG for the analysis component and deriving automatically from it a finite-state approximation that is used as the recognition language model. Using this technique, we have built an efficient translation system that is fast compared to others with comparably-sized language models.