Performance of the MVOCA silent speech interface across multiple speakers

Robin Hofe, Jie Bai, Lam A. Cheah, Stephen R. Ell, James M. Gilbert, Roger K. Moore, Phil D. Green

This paper investigates the performance of a silent speech interface (SSI) based on permanent-magnetic articulography (PMA) across several speakers. In a previously published study, the SSI was shown to be capable of distinguishing between voiced and unvoiced plosives ([b,p] and [d,t]) in data recorded from a single speaker; a surprising result in a system without access to speech acoustics. The study presented in this paper verifies this finding for three male native English speakers. Furthermore, the speech data used in this investigation was designed to shed light on the capability of the SSI to differentiate between a wider range of phones. A particularly interesting result is that it is possible to distinguish between voiced and unvoiced fricatives ([s,z] and [f,v]) as well as plosives, using PMA data.

doi: 10.21437/Interspeech.2013-311

Cite as: Hofe, R., Bai, J., Cheah, L.A., Ell, S.R., Gilbert, J.M., Moore, R.K., Green, P.D. (2013) Performance of the MVOCA silent speech interface across multiple speakers. Proc. Interspeech 2013, 1140-1143, doi: 10.21437/Interspeech.2013-311

@inproceedings{hofe13_interspeech,
  author={Robin Hofe and Jie Bai and Lam A. Cheah and Stephen R. Ell and James M. Gilbert and Roger K. Moore and Phil D. Green},
  title={{Performance of the MVOCA silent speech interface across multiple speakers}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={1140--1143},
  doi={10.21437/Interspeech.2013-311}
}