Automated Diagnosis and Assessment of Dysarthric Speech Using Relevant Prosodic Features

  • Kamil Lahcene Kadi
  • Sid Ahmed Selouani
  • Bachir Boudraa
  • Malika Boudraa
Conference paper

Abstract

In this paper, linear discriminant analysis (LDA) is combined with two automatic classification approaches, the Gaussian mixture model (GMM) and support vector machine (SVM), to automatically assess dysarthric speech. The front-end processing uses a set of prosodic features selected by LDA on the basis of their discriminative ability, with Wilks’ lambda as the significant measure to show the discriminant power. More than eight hundred sentences produced by nine American dysarthric speakers of the Nemours database are used throughout the experiments. Results show a best classification rate of 93 % with the LDA/SVM system achieved over four severity levels of dysarthria, ranged from not affected to the more seriously ill. This tool can aid speech therapist and other clinicians to diagnose, assess, and monitor dysarthria. Furthermore, it may reduce some of the costs associated with subjective tests.

Keywords

Dysarthria GMM LDA Nemours database Prosodic features Severity-level assessment SVM 

Notes

Acknowledgments

This work was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC).

References

  1. 1.
    C. Roth, in Encyclopedia of Clinical Neuropsychology, ed. by: B. Caplan, J. Deluca, J.S. Kreutzer (Springer, Heidelberg, 2011), pp. 905–908Google Scholar
  2. 2.
    S.-A. Selouani, H. Dahmani, R. Amami, H. Hamam, in SOCO 2011: Dysarthric Speech Classification Using Hierarchical Multilayer Perceptrons and Posterior Rhythmic Features. Proceedings of 6th International Conference. Soft Computing Models in Industrials and Environmental ApplicationsGoogle Scholar
  3. 3.
    American Speech-Language-Hearing Association [Online]. Available: http://www.asha.org
  4. 4.
    J.B. Polikoff, H.T. Bunnel, in ICPhS: The Nemours database of dysarthric speech: a perceptual analysis. Proceedings of 14th International Congress of Phonetic Sciences, 1999, pp. 783–786Google Scholar
  5. 5.
    S.-A. Selouani, H. Dahmani, R. Amami, H. Hamam, Using speech rhythm knowledge to improve dysarthric speech recognition. Int. J. Speech Technol. 15(1), 57–64 (2012)CrossRefGoogle Scholar
  6. 6.
    F. Rudzicz, in ICASSP 2009: Phonological Features in Discriminative Classification of Dysarthric Speech Google Scholar
  7. 7.
    M.S. Paja, T.H. Falk, in Automated Dysarthria Severity Classification for Improved Objective Intelligibility Assessment of Spastic Dysarthric Speech. Interspeech, 2012Google Scholar
  8. 8.
    X. Menendez-Pidal, J.B. Polikoff, S.M. Peters, J.E. Leonzio, H.T. Bunnell, in ICSLP: The Nemours Database of Dysarthric Speech. Fourth International Conference on Spoken Language, vol. 3 (IEEE, New York, 1996) pp. 1962–1965Google Scholar
  9. 9.
    L. Mary, B. Yegnanarayana, Extraction and representation of prosodic features for language and speaker recognition. Speech Commun. 50(10), 782–796 (2008)CrossRefGoogle Scholar
  10. 10.
    E. Shriberg, A. Stolcke, D. Hakkani, Prosody-based automatic segmentation of speech into sentences and topics. Speech Communication 32(1–2), 127–154 (2000). (Special Issue on Accessing Information in Spoken Audio)CrossRefGoogle Scholar
  11. 11.
    J.R. Duffy, Motor Speech Disorders: Clues to Neurologic Diagnosis, in Parkinson’s Disease and Movement Disorders, ed. by C.H. Adler, J.E. Ahlskog (Springer, Heidelberg, 2000), pp. 35–53CrossRefGoogle Scholar
  12. 12.
    K.L. Kadi, S.-A. Selouani, B. Boudraa, M. Boudraa, in WCE 2013: Discriminative Prosodic Features to Assess the Dysarthria Severity Levels. Proceedings of The World Congress on Engineering 2013, 3–5 July London. Lecture Notes in Engineering and Computer Science, pp. 2201–2205Google Scholar
  13. 13.
    R. Kent, H. Peters, P. Van-Lieshout, W. Hulstijn, Speech Motor Control in Normal and Disordered Speech (Oxford University Press, London, 2004)Google Scholar
  14. 14.
    J.T. Hart, R. Collier, A. Cohen, A Perceptual Study of Intonation (Cambridge University Press, Cambridge, 1990)CrossRefGoogle Scholar
  15. 15.
    L. Mary, in Extraction and Representation of Prosody for Speaker, Speech and Language Recognition (Springer Briefs in Speech Technology, 2012), chap. 1Google Scholar
  16. 16.
    H.F. Westzner, S. Schreiber, L. Amaro, Analysis of fundamental frequency, jitter, shimmer and vocal intensity in children with phonological disorders. Braz. J Orthinolaryngol. 71(5), 582–588 (2005)Google Scholar
  17. 17.
    Multi-Dimensional Voice Processing Program (MDVP), Kay Elemetrics Company: http://www.kayelemetrics.com
  18. 18.
    L. Baghai-Ravary, S.W. Beet, in Automatic Speech Signal Analysis for Clinical Diagnosis and Assessment of Speech Disorders. Springer Briefs in Electrical and Computer Engineering, 2013Google Scholar
  19. 19.
    J.M. Liss, L. White, S.L. Mattys, K. Lansford, A.J. Lotto, S.M. Spitzer, J.N. Caviness, Quantifying speech rhythm abnormalities in the dysarthrias. J Speech, Lang. Hear. Res. 52, 1334–1352 (2009)CrossRefGoogle Scholar
  20. 20.
    Calliope, La parole et son traitement automatique, Dunod, 1989Google Scholar
  21. 21.
    P. Boersma, D. Weenink, Praat, a system for doing phonetics by computer. Glot Int 5(9–10), 341–345 (2001)Google Scholar
  22. 22.
    C.E. Guerra, D.F. Lovey, in EMBS 2003: A Modern Approach to Dysarthria Classification. Proceedings of the 25th Annual International Conference of the IEEE, New York. Engineering in Medecine and Biology SocietyGoogle Scholar
  23. 23.
    Copyright IBM Corporation., 1989–2012. Available: http://www.ibm.com
  24. 24.
    A. El Ouardighi, A. El Akadi, D. Aboutadjine, in ISCCIII: Feature Selection on Supervised Classification Using Wilk’s Lambda Statistic. International Symposium on Computational Intelligence and Intelligent Informatics, 2007, pp. 51–55Google Scholar
  25. 25.
    A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum-likelihood from incomplete data via the EM algorithm. J. Acoust. Soc. Am. 39(1), 1–38 (1977)MATHMathSciNetGoogle Scholar
  26. 26.
    D. Istrate, E. Castelli, M. Vacher, L. Besacier, J. Serignat, Information extraction from sound for medical telemonitoring. IEEE Trans. Inf. Technol. Biomed. 10(2), 264–274 (2006)CrossRefGoogle Scholar
  27. 27.
    V.N. Vapnik, An overview of statistical learning theory. IEEE Trans. Neural Networks 10(5), 988–999 (1999)CrossRefGoogle Scholar
  28. 28.
    H. Gao, A. Guo, X. Yu, C. Li, in WiCOM’08: Rbf-Svm and its Application on Network Security Risk Evaluation. Proceedings of 4th International Conference on Wireless Communication, Networking and Mobile Computing, 2008Google Scholar
  29. 29.
    A. Fleury, M. Vacher, N. Noury, SVM-Based multimodal classification of Activities of daily living in health smart homes: sensors, algorithms, and first experimental results. IEEE Trans. Inf. Technol.Biomed. 14(2), 274–283 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Kamil Lahcene Kadi
    • 1
  • Sid Ahmed Selouani
    • 2
  • Bachir Boudraa
    • 1
  • Malika Boudraa
    • 1
  1. 1.Faculty of Electronics and Computer ScienceUniversity of Sciences and Technology Houari BoumedieneBab Ezzouar AlgiersAlgeria
  2. 2.Department of Information ManagementUniversity of MonctonMonctonCanada

Personalised recommendations