Detail publikačního výsledku

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

KOVÁČ, D.; MEKYSKA, J.; GALÁŽ, Z.; BRABENEC, L.; KOŠŤÁLOVÁ, M.; RAPCSAK, S.; REKTOROVÁ, I.

Originální název

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

Anglický název

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

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

acoustic analysis; Parkinson's disease; hypokinetic dysarthria; classification

Klíčová slova v angličtině

acoustic analysis; Parkinson's disease; hypokinetic dysarthria; classification

Autoři

KOVÁČ, D.; MEKYSKA, J.; GALÁŽ, Z.; BRABENEC, L.; KOŠŤÁLOVÁ, M.; RAPCSAK, S.; REKTOROVÁ, I.

Rok RIV

2022

Vydáno

30.08.2021

Nakladatel

IEEE

Místo

NEW YORK

ISBN

978-1-6654-2933-7

Kniha

2021 44th International Conference on Telecommunications and Signal Processing

Strany od

273

Strany do

277

Strany počet

5

URL

https://ieeexplore.ieee.org/document/9522597

BibTex

@inproceedings{BUT172226,
  author="Daniel {Kováč} and Jiří {Mekyska} and Zoltán {Galáž} and Luboš {Brabenec} and Milena {Košťálová} and Steven Z. {Rapcsak} and Irena {Rektorová}",
  title="Multilingual Analysis of Speech and Voice Disorders in Patients with Parkinson's Disease",
  booktitle="2021 44th International Conference on Telecommunications and Signal Processing",
  year="2021",
  pages="273--277",
  publisher="IEEE",
  address="NEW YORK",
  doi="10.1109/TSP52935.2021.9522597",
  isbn="978-1-6654-2933-7",
  url="https://ieeexplore.ieee.org/document/9522597"
}