Analysis of acoustic voice parameters for larynx pathology detection
https://doi.org/10.37661/1816-0301-2020-17-1-78-86
Abstract
The comparative study of two types of voice signal representation for larynx pathology detection is presented. Parameters obtained in clinical system lingWaves compared to parameters obtained by mel-frequency cepstral analysis. The classifier based on the probabilistic model (logistic regression) was designed to determine the suitability of given parameters for the larynx pathology detection problem. To train the classifier, the base of voice samples of 60 persons was recorded, 30 of which constitute the control group, and the other 30 had various diseases of the larynx (nodules of the vocal folds, laryngeal paralysis, or functional dysphonia). The results show that the classifier based on mel-frequency cepstral parameters (83,8 %) higher than the classifier based on parameters obtained in lingWaves (60,4 %).
About the Authors
M. I. Vashkevich
Belarusian State University of Informatics and Radioelectronics
Belarus
Maxim I. Vashkevich, Cand. Sci. (Eng.), Associate Professor of Computer Engineering Department
Belarus
Maxim I. Vashkevich, Cand. Sci. (Eng.), Associate Professor of Computer Engineering Department
A. A. Burak
Belarusian State University of Informatics and Radioelectronics
Belarus
Anton A. Burak, Student
Belarus
Anton A. Burak, Student
N. S. Kanoika
Republican Scientific and Practical Center of Otorhinolaryngology
Belarus
Natallia S. Kanoika, Head of the Phoniatric Department
Belarus
Natallia S. Kanoika, Head of the Phoniatric Department
V. S. Daldova
Republican Scientific and Practical Center of Otorhinolaryngology
Valeria S. Daldova, Phoniatrist of the Phoniatric Department
Valeria S. Daldova, Phoniatrist of the Phoniatric Department
References
1. Shilenkova V. V. Disfonii i golos. Dysphonies and Voice. Yaroslavl, Avers Pljus, 2018, 256 р. (in Russian).
2. Ermolayev V. G., Lebedeva N. F., Morozov V. P. Rukovodstvo po foniatrii. Phoniatrics Guide. Leningrad, Medicina, Leningradskoe otdelenie, 1970, 271 р. (in Russian).
3. Korotchenko V. V. Akusticheskij analiz golosa u detej v norme i pri zabolevaniyax gortani. Avtoref. dis. … kand. med. nauk. Acoustic Analysis of Voice in Children Is Normal and with Diseases of the Larynx. Cand. med. sci. diss. abstr. Ministerstvo zdravoohranenija i social'nogo razvitija Rossijskoj Federacii, Jaroslavskaja gosudarstvennaja medicinskaja akademija. Moscow, 2012, 24 р. (in Russian).
4. Fraile R., Sáenz-Lechón N., Godino-Llorente J., Osma-Ruiz V., Fredouille C. Automatic detection of laryngeal pathologies in records of sustained vowels by means of mel-frequency cepstral coefficient parameters and differentiation of patients by sex. Folia Phoniatrica Logopaedica, 2009, vol. 61, pp. 146–152.
5. Rilov A. S. Analiz rechi v raspoznajushhih sistemah. Speech Analysis in Recognition Systems. Minsk, Bestprint, 2003, 264 p. (in Russian).
6. Huang X., Acero A., Hon H.-W. Spoken Language Processing: a Guide to Theory, Algorithm and System Development. New Jersey, Prentice Hall, 2001, 1009 p.
7. Flach P. Machine Learning. The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, 2012, 409 p.
8. Tibshirani R. Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society, 1996, vol. 58, no. 1, pp. 267–288.
Review
For citations:
Vashkevich M.I., Burak A.A., Kanoika N.S., Daldova V.S. Analysis of acoustic voice parameters for larynx pathology detection. Informatics. 2020;17(1):78-86. (In Russ.) https://doi.org/10.37661/1816-0301-2020-17-1-78-86
Views: 1167
Email this article 