Acoustic analysis of voice for detection of speech disorder for amyotrophic lateral sclerosis
Abstract
A method of acoustic signal analysis with sustain vowel phonation for detection of amyotrophic lateral sclerosis (ALS) is considered. A method for segmentation of the voice signal into periods of the fundamental tone, which is used for evaluation of the jitter and shimmer parameters, is proposed. A comparison of two ALS detectors was performed. The first detector was trained using voice features extracted by the proposed method, while the second detector was trained using features obtained with PRAAT toolkit. The result showed a significant improvement (by 20 %) in the accuracy of detecting ALS disease using the proposed method.
About the Authors
M. I. Vashkevich
Белорусский государственный университет информатики и радиоэлектроники, Республика Беларусь
Belarus
Belarus
A. D. Gvozdovich
Белорусский государственный университет информатики и радиоэлектроники, Республика Беларусь
Belarus
Belarus
Y. N. Rushkevich
Республиканский научно-практический центр неврологии и нейрохирургии, Республика Беларусь
Belarus
Belarus
A. A. Petrovsky
Белорусский государственный университет информатики и радиоэлектроники, Республика Беларусь
Belarus
Belarus
References
1. Завалишин И.А. Боковой амиотрофический склероз. М.: ГЭОТАР - Медиа, 2009. 272 с.
2. Yunusova Y., Rosenthal J.S., Green J.R. Detection of bulbar ALS using a comprehensive speech assessment battery // Mater. 8th Int. workshop «MAVEBA». Florence, Italy, 16-18 December 2013. P. 217-220.
3. Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease / A. Tsnas [et al.] // IEEE Transactions on Biomedical Engineering. 2012. Vol. 59, № 5. P. 1264-1271.
4. Benda A., Jilbab A., Hammouch A. Voice assessments for detecting patients with neurological diseases using PCA and NPCA // Int. J. of Speech Technology. 2017. Vol. 20. P. 673-683.
5. Azarov E., Vashkevich M., Petrovsky A. Instantaneous pitch estimation based on RAPT framework // Proc. EUSIPCO'12. Bucharest, Romania, 27-31August 2012. P. 2787-2791.
6. Features extraction for the automatic detection of ALS disease from acoustic speech signals / M.I. Vashkevich [et al.] // Proc. of Int. conf. «SPA'2018». Poznan, Poland, 19-21 September 2018. P. 179-184.
7. Boesma P., Weenink D. Praat, a system for doing phonestica by computer // Glot Int. 2001. Vol. 5. P. 341-345.
Review
For citations:
Vashkevich M.I., Gvozdovich A.D., Rushkevich Y.N., Petrovsky A.A. Acoustic analysis of voice for detection of speech disorder for amyotrophic lateral sclerosis. Doklady BGUIR. 2018;(7):64-68. (In Russ.)
Views: 338
Email this article 