Parkinson's disease progression assessment from speech using GlVIM-UBM

被引：17

作者：

Arias-Vergara, T. ^{[1
]}

Vasquez-Correa, J. C. ^{[1
]}

Orozco-Arroyave, J. R. ^{[1
,2
]}

Vargas-Bonilla, J. F. ^{[1
]}

Noeth, E. ^{[2
]}

机构：

[1] Univ Antioquia UdeA, Fac Engn, Calle 70 52-21, Medellin, Colombia

[2] Friedrich Alexander Univ Erlangen Nurnberg, Pattern Recognit Lab, Nurnberg, Germany

来源：

17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES | 2016年

关键词：

Speech disorders; GMM-UBM; Parkinson's disease; user modeling;

D O I：

10.21437/Interspeech.2016-1122

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

The Gaussian Mixture Model Universal Background Model (GMM-UBM) approach is used to assess the Parkinson's disease (PD) progression per speaker. The disease progression is assessed individually per patient following a user modeling approach. Voiced and unvoiced segments are extracted and grouped separately to train the models. Additionally, the Bhattacharyya distances used to estimate the difference between the UBM and the user model. Speech recordings from 62 PD patients (34 male and 28 female) were captured from 2012 to 2015 in four recording sessions. The validation of the models is performed with recordings of 7 patients. All of the patients were diagnosed by a neurologist expert according to the MDS-UPDRS-III scale. The features used to model the speech of the patients are validated by doing a regression based on a Support Vector Regressor (SVR). According to the results, it is possible to track the disease progression with a Pearson's correlation of up to 0.60 with respect to the MDS-UPDRS-III labels.

引用

页码：1933 / 1937

页数：5

共 12 条

[1]

[Anonymous], 2015, 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5

[2]

[Anonymous], 1978, Biometrics, DOI [DOI 10.1007/978-0-387-73003-5, 10.1007/978-0-387-73003-5_196, DOI 10.1007/978-0-387-73003-5_196]

[3]

Asgari Meysam, 2010, IEEE Int Workshop Mach Learn Signal Process, V2010, P462, DOI 10.1109/MLSP.2010.5589118

[4] Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS): Scale Presentation and Clinimetric Testing Results [J].

Goetz, Christopher G. ;

Tilley, Barbara C. ;

Shaftman, Stephanie R. ;

Stebbins, Glenn T. ;

Fahn, Stanley ;

Martinez-Martin, Pablo ;

Poewe, Werner ;

Sampaio, Cristina ;

Stern, Matthew B. ;

Dodel, Richard ;

Dubois, Bruno ;

Holloway, Robert ;

Jankovic, Joseph ;

Kulisevsky, Jaime ;

Lang, Anthony E. ;

Lees, Andrew ;

Leurgans, Sue ;

LeWitt, Peter A. ;

Nyenhuis, David ;

Olanow, C. Warren ;

Rascol, Olivier ;

Schrag, Anette ;

Teresi, Jeanne A. ;

van Hilten, Jacobus J. ;

LaPelle, Nancy .

MOVEMENT DISORDERS, 2008, 23 (15) :2129-2170

[5] Biochemical aspects of Parkinson's disease [J].

Hornykiewicz, O .

NEUROLOGY, 1998, 51 (02) :S2-S9

[6]

Orozco-Arroyave JR, 2014, LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION

[7] Speaker verification using adapted Gaussian mixture models [J].

Reynolds, DA ;

Quatieri, TF ;

Dunn, RB .

DIGITAL SIGNAL PROCESSING, 2000, 10 (1-3) :19-41

[8]

Schuller B, 2015, 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, P478

[9] Progression of Voice and Speech Impairment in the Course of Parkinson's Disease: A Longitudinal Study [J].

Skodda, S. ;

Groenheit, W. ;

Mancinelli, N. ;

Schlegel, U. .

PARKINSONS DISEASE, 2013, 2013

[10] Accurate Telemonitoring of Parkinsons Disease Progression by Noninvasive Speech Tests [J].

Tsanas, Athanasios ;

Little, Max A. ;

McSharry, Patrick E. ;

Ramig, Lorraine O. .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2010, 57 (04) :884-893

← 1 2 →