User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

On the Use of the Correlation between Acoustic Descriptors for the Normal/Pathological Voices Discrimination

Primary tabs

Dubuisson, Thomas Dutoit, Thierry [UCL] Gosselin, Bernard Remacle, Marc [MONT]

This paper presents an analysis system aiming at discriminating between normal and pathological voices. Compared to literature of voice pathology assessment, it is characterised by two aspects. First the system is based on features inspired from voice pathology assessment and music information retrieval. Second the distinction between normal and pathological voices is simply based on the correlation between acoustic features, while more complex classifiers are common in literature. Based on the normal and pathological samples included the MEEI database, it has been found that using two features ( spectral decrease and first spectral tristimulus in the Bark scale) and their correlation leads to correct classification rates of 94.7% for pathological voices and 89.5% for normal ones. The system also outputs a normal/pathological factor aiming at giving an indication to the clinician about the location of a subject according to the database. Copyright (C) 2009 Thomas Dubuisson et al.

Document type Article de périodique (Journal article) – Comparative Study, Journal Article, Research Support, U.S. Gov't, P.H.S.
Access type Accès restreint
Publication date 2009
Language Anglais
Journal information "Eurasip Journal on Advances in Signal Processing" - Vol. 28, no. 1, p. 9-17 (2009)
Peer reviewed yes
Publisher Hindawi Publishing Corporation (New York)
issn 1687-6172
e-issn 1687-6180
Publication status Publié
Affiliation UCL - MD/NOPS - Département de neurologie et de psychiatrie
MESH Subject United States ; Temperature ; Phosphotransferases - blood ; Phenotype ; Pedigree ; Hydrogen-Ion Concentration ; Humans ; Hexokinase - metabolism ; Genes ; Gene Frequency ; European Continental Ancestry Group ; Erythrocytes - enzymology ; Alleles ; African Continental Ancestry Group
Links
  1. (1981)
  2. (2008)
  3. Moran R.J., Reilly R.B., de Chazal P., Lacy P.D., Telephony-Based Voice Pathology Assessment Using Automated Speech Analysis, 10.1109/tbme.2005.869776
  4. Michaelis Dirk, Fröhlich Matthias, Strube Hans Werner, Selection and combination of acoustic features for the description of pathologic voices, 10.1121/1.421305
  5. Alonso Jesus B., de Leon José, Alonso Itziar, Ferrer Miguel A., Automatic Detection of Pathologies in The Voice by HOS Based Parameters, 10.1155/s1110865701000336
  6. Medan Y., Yair E., Chazan D., Super resolution pitch determination of speech signals, 10.1109/78.80763
  7. Shama Kumara, krishna Anantha, Cholayya Niranjan U, Study of Harmonics-to-Noise Ratio and Critical-Band Energy Spectrum of Speech as Acoustic Indicators of Laryngeal and Voice Pathology, 10.1155/2007/85286
  8. 83, 700 (1997)
  9. (2006)
  10. Image and signal processing (2008)
  11. 3, 27 (1996)
  12. 103 (1998)
  13. Probability and Statistics (1974)
  14. (1967)
  15. 8, 185 (1937)
  16. (1961)
  17. 51, 162 (1982)
  18. Jensen Kristoffer, Multiple Scale Music Segmentation Using Rhythm, Timbre, and Harmony, 10.1155/2007/73205
  19. de Cheveigné Alain, Kawahara Hideki, YIN, a fundamental frequency estimator for speech and music, 10.1121/1.1458024
  20. (1990)
  21. (1973)
Bibliographic reference Dubuisson, Thomas ; Dutoit, Thierry ; Gosselin, Bernard ; Remacle, Marc. On the Use of the Correlation between Acoustic Descriptors for the Normal/Pathological Voices Discrimination. In: Eurasip Journal on Advances in Signal Processing, Vol. 28, no. 1, p. 9-17 (2009)
Permanent URL http://hdl.handle.net/2078.1/35480