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

Manny Rayner, Nikos Tsourakis, Jan Stanek


We present an open source toolkit for creating robust speech-to-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.


Cite as: Rayner, M., Tsourakis, N., Stanek, J. (2018) A Robust Context-Dependent Speech-to-Speech Phraselator Toolkit for Alexa. Proc. Interspeech 2018, 175-176.


@inproceedings{Rayner2018,
  author={Manny Rayner and Nikos Tsourakis and Jan Stanek},
  title={A Robust Context-Dependent Speech-to-Speech Phraselator Toolkit for Alexa},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={175--176}
}