Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease

Daniel Kovac; Jiri Mekyska; Zoltan Galaz; Lubos Brabenec; Milena Kostalova; Steven Z. Rapcsak; Irena Rektorova

doi:10.1109/TSP52935.2021.9522597

Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease

Daniel Kovac, Jiri Mekyska, Zoltan Galaz, Lubos Brabenec, Milena Kostalova, Steven Z. Rapcsak, Irena Rektorova

Neurology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Scopus citations

Abstract

Parkinson's disease (PD) is associated with several speech/voice disorders collectively referred to as hypokinetic dysarthria (HD). The main goal of this study is to identify acoustic features that support the diagnosis of PD while being independent of the language of a speaker. We recorded seven speech (e.g. monologue) and voice (e.g. sustained phonation) tasks in a cohort of 59 PD patients and 44 age-and gender-matched healthy controls (HC) speaking Czech or US English. A non-parametric test revealed that the best discrimination power has a measure quantifying the number of interword pauses per minute. In a consequent classification analysis, utilising logistic regression, we observed a drop in the classification accuracy from 72-73% to 67%, when moving from single-language modelling to the multilingual one. The results of this study suggest that especially the prosodic (pause-based) features could play a significant role in the automatic language-independent diagnosis of PD.

Original language	English (US)
Title of host publication	2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021
Editors	Norbert Herencsar
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	273-277
Number of pages	5
ISBN (Electronic)	9781665429337
DOIs	https://doi.org/10.1109/TSP52935.2021.9522597
State	Published - Jul 26 2021
Event	44th International Conference on Telecommunications and Signal Processing, TSP 2021 - Virtual, Brno, Czech Republic Duration: Jul 26 2021 → Jul 28 2021

Publication series

Name	2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021

Conference

Conference	44th International Conference on Telecommunications and Signal Processing, TSP 2021
Country/Territory	Czech Republic
City	Virtual, Brno
Period	7/26/21 → 7/28/21

Keywords

Parkinson's disease
acoustic analysis
classification
hypokinetic dysarthria

ASJC Scopus subject areas

Computer Networks and Communications
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/TSP52935.2021.9522597

Cite this

Kovac, D., Mekyska, J., Galaz, Z., Brabenec, L., Kostalova, M., Rapcsak, S. Z., & Rektorova, I. (2021). Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease. In N. Herencsar (Ed.), 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021 (pp. 273-277). (2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TSP52935.2021.9522597

Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease. / Kovac, Daniel; Mekyska, Jiri; Galaz, Zoltan et al.
2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021. ed. / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2021. p. 273-277 (2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kovac, D, Mekyska, J, Galaz, Z, Brabenec, L, Kostalova, M, Rapcsak, SZ & Rektorova, I 2021, Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease. in N Herencsar (ed.), 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021. 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021, Institute of Electrical and Electronics Engineers Inc., pp. 273-277, 44th International Conference on Telecommunications and Signal Processing, TSP 2021, Virtual, Brno, Czech Republic, 7/26/21. https://doi.org/10.1109/TSP52935.2021.9522597

Kovac D, Mekyska J, Galaz Z, Brabenec L, Kostalova M, Rapcsak SZ et al. Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease. In Herencsar N, editor, 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 273-277. (2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021). doi: 10.1109/TSP52935.2021.9522597

Kovac, Daniel ; Mekyska, Jiri ; Galaz, Zoltan et al. / Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease. 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021. editor / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 273-277 (2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021).

@inproceedings{764831008a8b4308b6147c1b47300ac4,

title = "Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease",

abstract = "Parkinson's disease (PD) is associated with several speech/voice disorders collectively referred to as hypokinetic dysarthria (HD). The main goal of this study is to identify acoustic features that support the diagnosis of PD while being independent of the language of a speaker. We recorded seven speech (e.g. monologue) and voice (e.g. sustained phonation) tasks in a cohort of 59 PD patients and 44 age-and gender-matched healthy controls (HC) speaking Czech or US English. A non-parametric test revealed that the best discrimination power has a measure quantifying the number of interword pauses per minute. In a consequent classification analysis, utilising logistic regression, we observed a drop in the classification accuracy from 72-73% to 67%, when moving from single-language modelling to the multilingual one. The results of this study suggest that especially the prosodic (pause-based) features could play a significant role in the automatic language-independent diagnosis of PD.",

keywords = "Parkinson's disease, acoustic analysis, classification, hypokinetic dysarthria",

author = "Daniel Kovac and Jiri Mekyska and Zoltan Galaz and Lubos Brabenec and Milena Kostalova and Rapcsak, {Steven Z.} and Irena Rektorova",

note = "Funding Information: This study has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under the Marie Sk{\l}odowska-Curie grant agreement no. 734718 (CoBeN), and from grants no. NU20-04-00294 and RVO (FNBr, 65269705) of the Czech Ministry of Health. Publisher Copyright: {\textcopyright} 2021 IEEE.; 44th International Conference on Telecommunications and Signal Processing, TSP 2021 ; Conference date: 26-07-2021 Through 28-07-2021",

year = "2021",

month = jul,

day = "26",

doi = "10.1109/TSP52935.2021.9522597",

language = "English (US)",

series = "2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "273--277",

editor = "Norbert Herencsar",

booktitle = "2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021",

}

TY - GEN

T1 - Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease

AU - Kovac, Daniel

AU - Mekyska, Jiri

AU - Galaz, Zoltan

AU - Brabenec, Lubos

AU - Kostalova, Milena

AU - Rapcsak, Steven Z.

AU - Rektorova, Irena

N1 - Funding Information: This study has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 734718 (CoBeN), and from grants no. NU20-04-00294 and RVO (FNBr, 65269705) of the Czech Ministry of Health. Publisher Copyright: © 2021 IEEE.

PY - 2021/7/26

Y1 - 2021/7/26

N2 - Parkinson's disease (PD) is associated with several speech/voice disorders collectively referred to as hypokinetic dysarthria (HD). The main goal of this study is to identify acoustic features that support the diagnosis of PD while being independent of the language of a speaker. We recorded seven speech (e.g. monologue) and voice (e.g. sustained phonation) tasks in a cohort of 59 PD patients and 44 age-and gender-matched healthy controls (HC) speaking Czech or US English. A non-parametric test revealed that the best discrimination power has a measure quantifying the number of interword pauses per minute. In a consequent classification analysis, utilising logistic regression, we observed a drop in the classification accuracy from 72-73% to 67%, when moving from single-language modelling to the multilingual one. The results of this study suggest that especially the prosodic (pause-based) features could play a significant role in the automatic language-independent diagnosis of PD.

AB - Parkinson's disease (PD) is associated with several speech/voice disorders collectively referred to as hypokinetic dysarthria (HD). The main goal of this study is to identify acoustic features that support the diagnosis of PD while being independent of the language of a speaker. We recorded seven speech (e.g. monologue) and voice (e.g. sustained phonation) tasks in a cohort of 59 PD patients and 44 age-and gender-matched healthy controls (HC) speaking Czech or US English. A non-parametric test revealed that the best discrimination power has a measure quantifying the number of interword pauses per minute. In a consequent classification analysis, utilising logistic regression, we observed a drop in the classification accuracy from 72-73% to 67%, when moving from single-language modelling to the multilingual one. The results of this study suggest that especially the prosodic (pause-based) features could play a significant role in the automatic language-independent diagnosis of PD.

KW - Parkinson's disease

KW - acoustic analysis

KW - classification

KW - hypokinetic dysarthria

UR - http://www.scopus.com/inward/record.url?scp=85115442210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115442210&partnerID=8YFLogxK

U2 - 10.1109/TSP52935.2021.9522597

DO - 10.1109/TSP52935.2021.9522597

M3 - Conference contribution

AN - SCOPUS:85115442210

T3 - 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021

SP - 273

EP - 277

BT - 2021 44th International Conference on Telecommunications and Signal Processing, TSP 2021

A2 - Herencsar, Norbert

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 44th International Conference on Telecommunications and Signal Processing, TSP 2021

Y2 - 26 July 2021 through 28 July 2021

ER -

Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this