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

Our Roger K Moore 's paper demonstrates how well magnetic sensors can capture phonetic detail without any direct access to voicing information!

http://www.sciencedirect.com/science/article/pii/S0167639312000167

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

Speech Communication

Volume 55, Issue 1, January 2013, Pages 22–32

 

  • a Department of Computer Science, The University of Sheffield, 211 Portobello, Sheffield S1 4DP, UK
  • b Hull and East Yorkshire Hospitals Trust, Castle Hill Hospital, Cottingham HU16 5JQ, UK
  • c Department of Engineering, The University of Hull, Kingston upon Hull, HU6 7RX, UK

 

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.

Keywords

  • Silent speech interfaces;
  • Clinical speech technology;
  • Articulography;
  • Multi-modal speech recognition;
  • Speech articulation

Maria Aretoulaki
Posted 30th November 2012 at 1:56 PM