期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2015
卷号：7
期号：2
DOI：10.15676/ijeei.2015.7.2.10
出版社：School of Electrical Engineering and Informatics
摘要：In order to develop the assessment of speech disorders for detecting patientswith Parkinson’s disease (PD), we have collected 34 sustained vowel / a /, from 34subjects including 17 PD patients. We subsequently extracted from 1 to 20 coefficientsof the Mel Frequency Cepstral Coefficients (MFCCs) from each individual. To extractthe voiceprint from each individual, we compressed the frames by calculating theiraverage value. For classification, we used the Leave-One-Subject-Out (LOSO)validation scheme and the Support Vector Machines (SVMs) with its different types ofkernels, (i.e.; RBF, Linear and polynomial). The best classification accuracy achievedwas 91.18% using the first 12 coefficients of the MFCCs by Linear kernels SVMs
关键词：Voice analysis; Parkinson’s disease; Mel Frequency Cepstral Coefficients;Voiceprint. Leave One Subject Out; Support Vector Machines
