Multilingual Analysis of Hypokinetic Dysarthria in Patients with Parkinson's disease

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU141298" target="_blank" >RIV/00216305:26220/21:PU141298 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf" target="_blank" >https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Multilingual Analysis of Hypokinetic Dysarthria in Patients with Parkinson's disease

Popis výsledku v původním jazyce

This article deals with the multilingual analysis of hypokinetic dysarthria (HD) in patients with Parkinson’s disease (PD). The goal is to identify acoustic features that have high discrimination power and that are independent of the language of a speaker. The speech corpus contains 59 PD patients and 44 healthy controls (HC) speaking in Czech (cs) and American English (en-US). Based on non-parametric statistical tests and logistic regression, we observed the best discrimination power has the speech index of rhythmicity (extracted from a reading text) and harmonic-to-noise ratio (extracted from a sustained vowel). We were able to identify PD with 67% sensitivity and 79% specificity in the Czech corpus and with 78% sensitivity and 67% specificity in the English one. The performance of the model was significantly lower when combining both datasets, thus suggesting language plays a significant role during the automatic assessment of HD.

Název v anglickém jazyce

Multilingual Analysis of Hypokinetic Dysarthria in Patients with Parkinson's disease

Popis výsledku anglicky

This article deals with the multilingual analysis of hypokinetic dysarthria (HD) in patients with Parkinson’s disease (PD). The goal is to identify acoustic features that have high discrimination power and that are independent of the language of a speaker. The speech corpus contains 59 PD patients and 44 healthy controls (HC) speaking in Czech (cs) and American English (en-US). Based on non-parametric statistical tests and logistic regression, we observed the best discrimination power has the speech index of rhythmicity (extracted from a reading text) and harmonic-to-noise ratio (extracted from a sustained vowel). We were able to identify PD with 67% sensitivity and 79% specificity in the Czech corpus and with 78% sensitivity and 67% specificity in the English one. The performance of the model was significantly lower when combining both datasets, thus suggesting language plays a significant role during the automatic assessment of HD.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/NU20-04-00294" target="_blank" >NU20-04-00294: Diagnostika onemocnění s Lewyho tělísky v prodromálním stadiu založená na analýze multimodálních dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů