Suboptimal Classifier for Dysarthria Assessment

  • Eduardo Castillo Guerra
  • Dennis F. Lovely
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)


This work is focused on the design and evaluation of a suboptimal classifier for dysarthria assessment. The classification relied on self organizing maps to discriminate 8 types of dysarthria and a normal group. The classification technique provided an excellent accuracy for assessment and enabled clinicians with a powerful relevance analysis of the input features. This technique also allows a bi-dimensional map that shows the spatial distribution of the data revealing important information about the different dysarthric groups.


Amyotrophic Lateral Sclerosis Linear Discriminant Analysis Input Feature Winning Neuron Speech Hear 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Michaelis, D., Strube, H.W.: Empirical study to test the independence of different acoustic voice parameters on a large voice database. Eurospeech proceedings 3, 1891–1894 (1995)Google Scholar
  2. 2.
    Michaelis, D., Gramss, T., Strube, H.W.: Glottal to noise excitation ratio – A new measure for describe pathological voices. Acust. Acta Acust. 83, 700–706 (1997)Google Scholar
  3. 3.
    Castillo-Guerra, E.: A modern approach to dysarthria classification. Ph.D. Thesis at University of New Brunswick. Canada (2002)Google Scholar
  4. 4.
    Klatt, D.H., Klatt, L.C.: Analysis, synthesis and perception of voice quality variations among female and male talkers. J. Acous. Soc. Am. 87(2) (1990)Google Scholar
  5. 5.
    Kent, R.D., Weismer, G., Kent, J.F., Houri, K.V., Duffy, J.R.: Acoustic studies of dysarthric speech: Methods, progress, and potential. J. Comm. Disord. 32, 141–186 (1999)CrossRefGoogle Scholar
  6. 6.
    Titze, I.R.: Recommendation on acoustic voice analysis, summary statement. In: Workshop on Acoustic Voice Analysis, Denver. Colorado (1994)Google Scholar
  7. 7.
    Kay Elemetrics Corp.: Disordered speech database. Massachusetts Eye and Ear Infirmary. Voice and Speech Lab. Boston. M.A. Ver. 1.03 (1994)Google Scholar
  8. 8.
    Darley, F.L., Aronson, A.E., Brown, J.R.: Differential diagnostic patterns of dysarthrias. J. Speech Hear. Res. 12, 462–496 (1969a)Google Scholar
  9. 9.
    Simmons, K.C., Mayo, R.: The use of the Mayo Clinic system for differential diagnosis of dysarthria. J. Comm. Disord. 30, 117–132 (1997)CrossRefGoogle Scholar
  10. 10.
    Murdoch, B.E., Chenery, H.J.: Dysarthria, a physiological approach to assessment and treatment. Singular Publishing Group Inc. (August 1997)Google Scholar
  11. 11.
    Callan, E.D., Roy, N., Tasko, S.M.: Self organized maps for the classification of normal and disordered female voices. J. Speech Hear. Res. 42, 355–366 (1999)Google Scholar
  12. 12.
    Kohonen, T.: Self-organized maps, pp. 77–127. Springer, Berlin (1995)Google Scholar
  13. 13.
    Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J.: SOM_PAK: The Self-Organizing Map Program Package. Technical Report A31. Helsinki University of Technology. Laboratory of Computer and Information Science. FIN-02150 Espoo. Finland (1996)Google Scholar
  14. 14.
    Darley, F.L., Aronson, A.E., Brown, J.R.: Differential diagnostic patterns of dysarthria. J. Speech Hear. Res. 12, 246–249 (1969a)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Eduardo Castillo Guerra
    • 1
  • Dennis F. Lovely
    • 2
  1. 1.Centre for Studies on Electronics and Information TechnologiesCentral University “Marta Abreu” of Las VillasSanta ClaraCuba
  2. 2.Department of Electrical EngineeringUniversity of New BrunswickFrederictonCanada

Personalised recommendations