Healthy/Esophageal Speech Classification using Features based on Speech Production and Audition Mechanisms

Sofia Ben Jebara

2013

Abstract

This paper focuses on the classification of speech sequences into two classes: healthy speech and esophageal speech. Two kinds of features are selected: those based on speaker speech production mechanism and those using listener auditory system properties. Two classification strategies are used: the Discriminant Analysis and the GMM based bayesian classifier. Experiments, conducted with a large database, show classification accuracy using both features. Moreover, auditory based features are the best since error rates tend to be null.

References

  1. Arslan, L. M. and Hansen, J. H. L. (1999). Selective training for hidden markovian models with applications to speech classification. In IEEE Trans. on Speech and Audio Processing. Vol. 7, no.1, pp. 46-54.
  2. Atal, B. S. and Rabiner, L. R. (1996). A new pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition. In IEEE Trans. Acoust. Speech and Signal Processing. ASSP24, pp. 201-212.
  3. BenJebara, S. (2006). Multi-band coherence features for voiced-unvoiced-silence speech classification. In Proc. of the Int. Conf. on Information and Communication Technologies: from Theory to Applications ICTTA. Damascus-Syria.
  4. BenJebara, S. (2008). Voice activity detection using periodioc/aperiodic coherence features. In Proc. of the 16th European Signal Processing Conf. EUSIPCO. Lauzane-Switzerland.
  5. Childers, D. G., Hahn, M., and Larar, J. N. (1989). Silent and voiced/unvoiced/mixed excitation (fourway) classification of speech. In IEEE Trans. Acoust. Speech and Signal Processing. vol. ASSP-37, no. 11, pp. 1171-1774.
  6. ITU-T (1996). Recommandation g729 annex b.
  7. Kasuya, H. and Ogawa, S. (1986). Normalized noise energy as an acoustic measure to evaluate pathologic voice. In Journal of the Acoustical Society of America. pp. 34-43.
  8. Liao, L. and Gregory, M. A. (1999). Algorithms for speech classification. In Proc. of the Int. Symp. on Signal Processing and its Applications ISSPA. BrisbaneAustralia.
  9. Orlikoff, P. B. R. (2000). Clinical measurement of speech and voice. CA:Singular Publishing Group, 2nd edition.
  10. Rabiner, L. R. and Juang, B. H. (1993). Fundamentals of speech recognition. Prentice-Hall, New Jersey.
  11. Zwicker, E. (1961). Subdivision of the audible frequency range into critical bands. In The J. of Acoustical Society of America.
Download


Paper Citation


in Harvard Style

Ben Jebara S. (2013). Healthy/Esophageal Speech Classification using Features based on Speech Production and Audition Mechanisms . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013) ISBN 978-989-8565-36-5, pages 99-104. DOI: 10.5220/0004181500990104


in Bibtex Style

@conference{biosignals13,
author={Sofia Ben Jebara},
title={Healthy/Esophageal Speech Classification using Features based on Speech Production and Audition Mechanisms},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)},
year={2013},
pages={99-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004181500990104},
isbn={978-989-8565-36-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)
TI - Healthy/Esophageal Speech Classification using Features based on Speech Production and Audition Mechanisms
SN - 978-989-8565-36-5
AU - Ben Jebara S.
PY - 2013
SP - 99
EP - 104
DO - 10.5220/0004181500990104