Recognition and real time performances of a lightweight ultrasound based silent speech interface employing a language model

Jun Cai, Bruce Denby, Pierre Roussel, Gérard Dreyfus, Lise Crevier-Buchman

The work presents advances in the implementation of an ultrasound based silent speech interface system. Use of a portable acquisition device, a visual speech recognizer system with a language model, and real time tests with the Julius system are described. Experiments with two types of visual feature extraction are also presented. Results show that good recognition and real time performance can be obtained with a portable silent speech interface employing a language model.

doi: 10.21437/Interspeech.2011-410

Cite as: Cai, J., Denby, B., Roussel, P., Dreyfus, G., Crevier-Buchman, L. (2011) Recognition and real time performances of a lightweight ultrasound based silent speech interface employing a language model. Proc. Interspeech 2011, 1005-1008, doi: 10.21437/Interspeech.2011-410

@inproceedings{cai11_interspeech,
  author={Jun Cai and Bruce Denby and Pierre Roussel and Gérard Dreyfus and Lise Crevier-Buchman},
  title={{Recognition and real time performances of a lightweight ultrasound based silent speech interface employing a language model}},
  year=2011,
  booktitle={Proc. Interspeech 2011},
  pages={1005--1008},
  doi={10.21437/Interspeech.2011-410}
}