en
Proceedings chapter
Open access
English

A Robust Medical Speech-to-Speech/Speech-to-Sign Phraselator

Published inInterspeech
Publication date2017
Abstract

We present BabelDr, a web-enabled spoken-input phraselator for medical domains, which has been developed at Geneva University in a collaboration between a human language technology group and a group at the University hospital. The current production version of the system translates French into Arabic, using exclusively rule-based methods, and has performed credibly in simulated triaging tests with standardised patients. We also present an experimental version which combines largevocabulary recognition with the main rule-based recogniser; offline tests on unseen data suggest that the new architecture adds robustness while more than halving the 2-best semantic error rate. The experimental version translates from spoken English into spoken French and also two sign languages.

Citation (ISO format)
AHMED, Farhia et al. A Robust Medical Speech-to-Speech/Speech-to-Sign Phraselator. In: Interspeech. [s.l.] : [s.n.], 2017.
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
  • PID : unige:96955
591views
116downloads

Technical informations

Creation09/15/2017 2:56:00 PM
First validation09/15/2017 2:56:00 PM
Update time03/15/2023 2:02:34 AM
Status update03/15/2023 2:02:33 AM
Last indexation05/02/2024 7:30:43 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack