Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F23%3A00370047" target="_blank" >RIV/68407700:21460/23:00370047 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.2478/msr-2023-0033" target="_blank" >https://doi.org/10.2478/msr-2023-0033</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.2478/msr-2023-0033" target="_blank" >10.2478/msr-2023-0033</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection

Popis výsledku v původním jazyce

Speech is one of the most serious manifestations of Parkinson's disease (PD). Sophisticated language/speech models have already demonstrated impressive performance on a variety of tasks, including classification. By analysing large amounts of data from a given setting, these models can identify patterns that would be difficult for clinicians to detect. We focus on evaluating the performance of a large self-supervised speech representation model, wav2vec, for PD classification. Based on the computed wav2vec embedding for each available speech signal, we calculated two sets of 512 derived features, wav2vec-sum and wav2vec-mean. Unlike traditional signal processing methods, this approach can learn a suitable representation of the signal directly from the data without requiring manual or hand-crafted feature extraction. Using an ensemble random forest classifier, we evaluated the embedding-based features on three different healthy vs. PD datasets (participants rhythmically repeat syllables /pa/, Italian dataset and English dataset). The obtained results showed that the wav2vec signal representation was accurate, with a minimum area under the receiver operating characteristic curve (AUROC) of 0.77 for the /pa/ task and the best AUROC of 0.98 for the Italian speech classification. The findings highlight the potential of the generalisability of the wav2vec features and the performance of these features in the cross-database scenarios. 2023 Ondřej Klempíř et al., published by Sciendo.

Název v anglickém jazyce

Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection

Popis výsledku anglicky

Speech is one of the most serious manifestations of Parkinson's disease (PD). Sophisticated language/speech models have already demonstrated impressive performance on a variety of tasks, including classification. By analysing large amounts of data from a given setting, these models can identify patterns that would be difficult for clinicians to detect. We focus on evaluating the performance of a large self-supervised speech representation model, wav2vec, for PD classification. Based on the computed wav2vec embedding for each available speech signal, we calculated two sets of 512 derived features, wav2vec-sum and wav2vec-mean. Unlike traditional signal processing methods, this approach can learn a suitable representation of the signal directly from the data without requiring manual or hand-crafted feature extraction. Using an ensemble random forest classifier, we evaluated the embedding-based features on three different healthy vs. PD datasets (participants rhythmically repeat syllables /pa/, Italian dataset and English dataset). The obtained results showed that the wav2vec signal representation was accurate, with a minimum area under the receiver operating characteristic curve (AUROC) of 0.77 for the /pa/ task and the best AUROC of 0.98 for the Italian speech classification. The findings highlight the potential of the generalisability of the wav2vec features and the performance of these features in the cross-database scenarios. 2023 Ondřej Klempíř et al., published by Sciendo.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

<a href="/cs/project/LX22NPO5107" target="_blank" >LX22NPO5107: Národní ústav pro neurologický výzkum</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

Measurement Science Review

ISSN

1335-8871

e-ISSN

1335-8871

Svazek periodika

23

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

SK - Slovenská republika

Počet stran výsledku

8

Strana od-do

260-267

Kód UT WoS článku

001111312600002

EID výsledku v databázi Scopus

2-s2.0-85178023933