MedSLT: a limited-domain unidirectional grammar-based medical speech translator

Authors:
Manny Rayner;Pierrette Bouillon;Nikos Chatzichrisafis;Marianne Santaholma;Marianne Starlander;Beth Ann Hockey;Yukie Nakao;Hitoshi Isahara;Kyoko Kanzaki
Affiliations:
University of Geneva, Geneva, Switzerland;University of Geneva, Geneva, Switzerland;University of Geneva, Geneva, Switzerland;University of Geneva, Geneva, Switzerland;University of Geneva, Geneva, Switzerland;UCSC/NASA Ames Research Center, Moffet Field, CA;National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan;National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan;National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan
Venue:
MST '06 Proceedings of the Workshop on Medical Speech Translation
Year:
2006

Citing 2
Cited 0

An open source environment for compiling typed unification grammars into speech recognisers

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
Putting Linguistics into Speech Recognition: The Regulus Grammar Compiler (Studies in Computational Linguistics (Stanford, Calif.).)

Putting Linguistics into Speech Recognition: The Regulus Grammar Compiler (Studies in Computational Linguistics (Stanford, Calif.).)

Quantified Score

Hi-index	0.00

Visualization

Abstract

MedSLT is a unidirectional medical speech translation system intended for use in doctor-patient diagnosis dialogues, which provides coverage of several different language pairs and subdomains. Vocabulary ranges from about 350 to 1000 surface words, depending on the language and subdomain. We will demo both the system itself and the development environment, which uses a combination of rule-based and data-driven methods to construct efficient recognisers, generators and transfer rule sets from small corpora.