Skip to main content

Research Repository

Advanced Search

Small-vocabulary speech recognition using a silent speech interface based on magnetic sensing

Rybchenko, Sergey I.; Gilbert, James M.; Hofe, Robin; Ell, Stephen R.; Fagan, Michael J.; Gilbert, James; Green, Phil D.; Moore, Roger K.; Rybchenko, Sergey

Authors

Sergey I. Rybchenko

James M. Gilbert

Robin Hofe

Stephen R. Ell

Phil D. Green

Roger K. Moore



Abstract

This paper reports on word recognition experiments using a silent speech interface based on magnetic sensing of articulator movements. A magnetic field was generated by permanent magnet pellets fixed to relevant speech articulators. Magnetic field sensors mounted on a wearable frame measured the fluctuations of the magnetic field during speech articulation. These sensor data were used in place of conventional acoustic features for the training of hidden Markov models. Both small vocabulary isolated word recognition and connected digit recognition experiments are presented. Their results demonstrate the ability of the system to capture phonetic detail at a level that is surprising for a device without any direct access to voicing information.

Citation

Hofe, R., Ell, S. R., Fagan, M. J., Gilbert, J., Green, P. D., Moore, R. K., & Rybchenko, S. (2013). Small-vocabulary speech recognition using a silent speech interface based on magnetic sensing. Speech communication, 55(1), 22-32. https://doi.org/10.1016/j.specom.2012.02.001

Journal Article Type Article
Online Publication Date Feb 15, 2012
Publication Date Jan 1, 2013
Deposit Date Nov 13, 2014
Publicly Available Date
Journal Speech Communication
Print ISSN 0167-6393
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 55
Issue 1
Pages 22-32
DOI https://doi.org/10.1016/j.specom.2012.02.001
Keywords Silent speech interfaces; Clinical speech technology; Articulography; Multi-modal speech recognition; Speech articulation
Public URL https://hull-repository.worktribe.com/output/467143
Publisher URL https://www.sciencedirect.com/science/article/pii/S0167639312000167?via%3Dihub#!