A Neural Network Based Approach to Objective Voice Quality Assessment

  • R. T. Ritchings
  • G. V. Conroy
  • M. A. McGillion
  • C. J. Moore
  • N. Slevin
  • S. Winstanley
  • H. Woods

Abstract

Voice quality is of fundamental importance to the patient following treatment of cancer of the larynx. Current techniques for voice analysis are slow, mainly subjective, and based on limited numbers of retrospective studies. This study is concerned with the development of an on-line system which encapsulates the expert knowledge of the Speech and Language Therapist in such a way as to provide an objective and consistent assessment of voice quality for staging and treatment monitoring of cancer of the larynx.

After discussions with the Speech and Language Therapist it was concluded that their expert knowledge was related to subtle variations in the frequency structure in a patient’s stylised speech. In order to identify the frequency components that can be used to provide an objective classification and assessment of a patient’s voice quality, appropriate parameters were extracted from a segment of speech recorded from 20 male patients with cancer of the larynx and 20 male volunteers who were considered as having normal voice quality. These parameters were then presented to a feedforward Artificial Neural Network known as the Multi-Layer Perceptron. This Multi-Layer Perceptron was shown to be able to distinguish between normal, i.e. non-cancerous, subjects and patients having cancer of the larynx, achieving a classification accuracy of between 85% and 90%. These results provide the basis for an extension of this work into a practical system that may be utilised by the Speech and Language Therapist during clinical examinations to provide an objective measure of voice quality.

Keywords

Entropy Phonate 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fourcin AJ, Abberton E, Miller D, Howell D. Laryngograph: Speech pattern element tools for therapy, training and assessment. European Journal of Disorders of Comunication, 1995; 30; 2: 101–115.CrossRefGoogle Scholar
  2. 2.
    Moore CJ, Slevin N, Ritchings RT & Chi KY. An approach to objective voice quality assessment for staging and treatment monitoring of cancer of the larynx. World Congress for Medical Physics and Biological Engineering, Nice, France, 1997.Google Scholar
  3. 3.
    Tadeusiewicz R, Wszolek W, Modrzejewski M. The evaluation of speech deformation treated for larynx cancer using neural network and pattern recognition methods. International conference on Engineering Applications of Neural Networks. EANN’98, Gibraltar, 1998.Google Scholar
  4. 4.
    Gavidia-Ceballos L, Hansen JHL. Direct speech feature estimation using an iterative EM algorithm for vocal fold pathology detection. IEEE Trans. on Biomedical Engineering. April 1996; 43; 4: 373–383.CrossRefGoogle Scholar
  5. 5.
    Aref A, Dworkin J, Syamala D, Denton L, Fontanesi, J. Objective evaluation of the quality of voice following radiation therapy for T1 glottic cancer. Radiotherapy and Oncology. 1997;45:149–153.CrossRefGoogle Scholar
  6. 6.
    Akers G, Lennig M. Intonation in text-to-speech synthesis: Evaluation of algorithms. J. Acoustical Society of America. 1985;77:2157–2165.CrossRefGoogle Scholar
  7. 7.
    Tarassenko L. A guide to neural computing applications. NCAF, Arnold, London, 1998.Google Scholar
  8. 8.
    Kohonen T. The Self-Organising Map. Proc. IEEE, 1990;78:1464–1480.CrossRefGoogle Scholar
  9. 9.
    Haykin S. Neural Networks: A Comprehensive Foundation. Englewood Cliffs, NJ: Macmillan, 1994.MATHGoogle Scholar
  10. 10.
    Bishop CM. Neural Networks for Pattern Recognition. Oxford University Press, Oxford, 1995.Google Scholar
  11. 11.
    Richard MD, Lippman RP. Neural network classifiers estimate Bayesian a-posteriori probabilities. Neural Computation, 1991;3:461–483.CrossRefGoogle Scholar
  12. 12.
    DeVilliers J, Barnard E. Backpropagation neural nets with one and two hidden layers. IEEE Transactions on Neural Networks, 1992;4:136–141.CrossRefGoogle Scholar
  13. 13.
    Moore CJ, Winstanley, S., Woods, et al. Computerising the evaluation of voice quality from impedance data for patients with cancer of the larynx. Unpublished, 1997.Google Scholar

Copyright information

© Springer-Verlag London Limited 1999

Authors and Affiliations

  • R. T. Ritchings
    • 1
  • G. V. Conroy
    • 1
  • M. A. McGillion
    • 1
  • C. J. Moore
    • 2
  • N. Slevin
    • 3
  • S. Winstanley
    • 4
  • H. Woods
    • 4
  1. 1.Multimedia Signal Processing Group, Department of ComputationUMISTManchesterUK
  2. 2.NorthWest Medical PhysicsChristie Hospital NHS TrustManchesterUK
  3. 3.Christie Hospital NHS TrustManchesterUK
  4. 4.South Manchester University Hospitals TrustWithington HospitalManchesterUK

Personalised recommendations