en
Proceedings chapter
Open access
English

A Robust Context-Dependent Speech-to-Speech Phraselator Toolkit for Alexa

Published inInterspeech 2018, p. 175-176
Presented at Hyderabad, India, 2-6 September 2018
Publication date2018
Abstract

We present an open source toolkit for creating robust speechto-speech phraselators, suitable for medical and other safety critical domains, that can be hosted on the Amazon Alexa platform. Supported functionality includes context-dependent translation of incomplete utterances. We describe a preliminary evaluation on an English medical examination grammar.

Keywords
  • Alexa
  • Speech translation
  • Medical applications
  • Robustness
  • Context-dependence
Citation (ISO format)
RAYNER, Emmanuel, TSOURAKIS, Nikolaos, STANEK, Jan. A Robust Context-Dependent Speech-to-Speech Phraselator Toolkit for Alexa. In: Interspeech 2018. Hyderabad, India. [s.l.] : [s.n.], 2018. p. 175–176.
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
  • PID : unige:108708
401views
130downloads

Technical informations

Creation09/28/2018 2:32:00 PM
First validation09/28/2018 2:32:00 PM
Update time03/15/2023 8:43:41 AM
Status update03/15/2023 8:43:41 AM
Last indexation01/17/2024 3:40:39 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack