Proceedings chapter
OA Policy
English

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

Presented atHyderabad, India, 2-6 September 2018
Published inInterspeech 2018, p. 175-176
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
450views
161downloads

Technical informations

Creation28/09/2018 14:32:00
First validation28/09/2018 14:32:00
Update time15/03/2023 08:43:41
Status update15/03/2023 08:43:41
Last indexation31/10/2024 11:14:05
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack