Restoring speech following total removal of the larynx by a learned transformation from sensor data to acoustics.

Journal: The Journal of the Acoustical Society of America
PMID: 28372104

Abstract

Total removal of the larynx may be required to treat laryngeal cancer: speech is lost. This article shows that it may be possible to restore speech by sensing movement of the remaining speech articulators and use machine learning algorithms to derive a transformation to convert this sensor data into an acoustic signal. The resulting "silent speech," which may be delivered in real time, is intelligible and sounds natural. The identity of the speaker is recognisable. The sensing technique involves attaching small, unobtrusive magnets to the lips and tongue and monitoring changes in the magnetic field induced by their movement.

Authors

  • James M Gilbert
    School of Engineering, University of Hull, Kingston upon Hull, United Kingdom J.M.Gilbert@Hull.ac.uk.
  • Jose A Gonzalez
    Department of Computer Science, University of Sheffield, Sheffield, United Kingdom J.Gonzalez@Sheffield.ac.uk.
  • Lam A Cheah
    School of Engineering, University of Hull, Kingston upon Hull, United Kingdom L.Cheah@Hull.ac.uk.
  • Stephen R Ell
    Hull and East Yorkshire Hospitals Trust, Castle Hill Hospital, Cottingham, United Kingdom srell@doctors.org.uk.
  • Phil Green
    Department of Computer Science, University of Sheffield, Sheffield, United Kingdom P.Green@Sheffield.ac.uk, R.K.Moore@Sheffield.ac.uk.
  • Roger K Moore
    Department of Computer Science, University of Sheffield, Sheffield, United Kingdom P.Green@Sheffield.ac.uk, R.K.Moore@Sheffield.ac.uk.
  • Ed Holdsworth
    Practical Control Limited, Sheffield, United Kingdom Ed.holdsworth@practicalcontrol.com.

Keywords

External Resources

Popular Topics
Recent Journals