Parkinson's Disease Diagnosis Based on Multivariate Deep Features of Speech Signal

Khojasteh, P, Puzhavakkathu Madom Viswanatha, R, Aliahmad, B, Ragnav, S, Zham, P and Kumar, D 2018, 'Parkinson's Disease Diagnosis Based on Multivariate Deep Features of Speech Signal', in Proceedings of the 2nd IEEE Life Sciences Conference (LSC 2018), Montreal, Quebec, Canada, 28-30 October 2018, pp. 187-190.


Document type: Conference Paper
Collection: Conference Papers

Title Parkinson's Disease Diagnosis Based on Multivariate Deep Features of Speech Signal
Author(s) Khojasteh, P
Puzhavakkathu Madom Viswanatha, R
Aliahmad, B
Ragnav, S
Zham, P
Kumar, D
Year 2018
Conference name LSC 2018
Conference location Montreal, Quebec, Canada
Conference dates 28-30 October 2018
Proceedings title Proceedings of the 2nd IEEE Life Sciences Conference (LSC 2018)
Publisher IEEE
Place of publication United States
Start page 187
End page 190
Total pages 4
Abstract Parkinson's disease (PD) is known as neurodegenerative disorder causing speech impairment in patients. Therefore, voice recording has been used as useful tool for diagnosis of PD. For the first time in this study, we have tested the effectiveness of deep convolutional neural network (DCNN) in distinguishing between Parkinson's and healthy voices using spectral features from sustained phoneme /a/ (as pronounced in car). Various designs of the DCNN architecture were investigated on raw pathological and healthy voices of varying lengths. This study also investigated the effect of parameters such as frame size, number of convolutional layers and feature maps as well as topology of fully connected layers on the accuracy of the classification outcome. The best network achieved accuracy of 75.7% corresponding on 815 ms of data for distinguishing between Parkinson's and healthy samples. This work has demonstrated that online speech recording has the potential for being used to screening people for Parkinson's disease.
Subjects Biomedical Engineering not elsewhere classified
Signal Processing
DOI - identifier 10.1109/LSC.2018.8572136
Copyright notice © 2018 IEEE
ISBN 9781538667095
Versions
Version Filter Type
Altmetric details:
Access Statistics: 18 Abstract Views  -  Detailed Statistics
Created: Thu, 31 Jan 2019, 11:26:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us