Robust Pathological Voice Detection Based on Component Information from HMM

  • M. Sarria-Paja
  • G. Castellanos-Domínguez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7015)

Abstract

Short–time parameters combined with dynamic classifiers such as Hidden Markov Models have been classically used in pathological voice detection systems, however most of the approaches rely in complex procedures or addition of new parameters that increases the time processing and it does not reflect in a better system performance. This paper presents an approach that improves the standard scheme for Hidden Markov Models based classification oriented to voice pathological identification. This approach uses HMMs to derive discriminative features defined by specific components of individual models, such features span an HMM–induced vector space where a feature based classifier can be trained. Results show that the discussed methodology outperforms significantly the accuracy in a classification system comparing with the standard classification scheme. As a result a high accuracy can be achieved by using a relatively simple procedure to generate an optimal decision boundary. Results are provided using the MEEIVL voice disorder database.

Keywords

HMM Vector Induced Space Pathological voice classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arias-Londono, J., Godino-Llorente, J., Saenz-Lechon, N., Osma-Ruiz, V., Castellanos-Dominguez, G.: An improved method for voice pathology detection by means of a HMM-based feature space transformation. Pattern Recognition 43(9), 3100–3112 (2010)CrossRefMATHGoogle Scholar
  2. 2.
    Bicego, M., Pekalska, E., Tax, D.M., Duin, R.P.: Component-based discriminative classification for hidden markov models. Pattern Recognition 42(11), 2637–2648 (2009)CrossRefMATHGoogle Scholar
  3. 3.
    Duda, R., Hart, P., Stork, D.: Pattern classification. Pattern Classification and Scene Analysis: Pattern Classification. Wiley (2001)Google Scholar
  4. 4.
    Gomez, P., Godino, J.I., Rodriguez, F., Diaz, F., Nieto, V., Alvarez, A., Rodellar, V.: Evidence of vocal cord pathology from the mucosal wave cepstral contents, vol. 5, pp. V-437–V-440 (May 17-21, 2004)Google Scholar
  5. 5.
    Li, X., Jiang, H., Liu, C.: Large margin hmms for speech recognition (2005)Google Scholar
  6. 6.
    Massachusetts Eye and Ear Infirmary: Voice disorders database, version.1.03 (cd-rom). Kay Elemetrics Corp., Lincoln Park, NJ (1994)Google Scholar
  7. 7.
    Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  8. 8.
    Saenz-Lechon, N., Godino-Llorente, J., Osma-Ruiz, V., Gomez-Vilda, P.: Methodological issues in the development of automatic systems for voice pathology detection. Biomedical Signal Processing and Control 1(2), 120–128 (2006)CrossRefMATHGoogle Scholar
  9. 9.
    Sarria-Paja, M., Castellanos-Dominguez, G., Delgado-Trejos, E.: A new approach to discriminative hmm training for pathological voice classification. In: Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 4674–4677 (2010)Google Scholar
  10. 10.
    Schluter, R., Macherey, W., Muller, B., Ney, H.: Comparison of discriminative training criteria and optimization methods for speech recognition. Speech Communication 34(3), 287–310 (2001)CrossRefMATHGoogle Scholar
  11. 11.
    Sin, B., Kim, J.H.: Nonstationary hidden markov model. Signal Processing 46(1), 31–46 (1995)CrossRefMATHGoogle Scholar
  12. 12.
    Vaseghi, S.V.: State duration modelling in hidden markov models. Signal Processing 41(1), 31–41 (1995)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • M. Sarria-Paja
    • 1
  • G. Castellanos-Domínguez
    • 2
  1. 1.Intelligent Machines and Pattern Recognition GroupInstituto Tecnológico MetropolitanoColombia
  2. 2.Signal Processing and Recognition GroupUniversidad Nacional de ColombiaColombia

Personalised recommendations