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

Farhia Ahmed, Pierrette Bouillon, Chelle Destefano, Johanna Gerlach, Sonia Halimi, Angela Hooper, Manny Rayner, Hervé Spechbach, Irene Strasly, Nikos Tsourakis


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 large-vocabulary 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.


Cite as: Ahmed, F., Bouillon, P., Destefano, C., Gerlach, J., Halimi, S., Hooper, A., Rayner, M., Spechbach, H., Strasly, I., Tsourakis, N. (2017) A Robust Medical Speech-to-Speech/Speech-to-Sign Phraselator. Proc. Interspeech 2017, 3433-3434.


@inproceedings{Ahmed2017,
  author={Farhia Ahmed and Pierrette Bouillon and Chelle Destefano and Johanna Gerlach and Sonia Halimi and Angela Hooper and Manny Rayner and Hervé Spechbach and Irene Strasly and Nikos Tsourakis},
  title={A Robust Medical Speech-to-Speech/Speech-to-Sign Phraselator},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={3433--3434}
}