Analyzing Wav2Vec 1.0 Embeddings for Cross-Database Parkinson’s Disease Detection and Speech Features Extraction

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F24%3A00377182" target="_blank" >RIV/68407700:21460/24:00377182 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.3390/s24175520" target="_blank" >https://doi.org/10.3390/s24175520</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/s24175520" target="_blank" >10.3390/s24175520</a>

Result language

angličtina

Original language name

Analyzing Wav2Vec 1.0 Embeddings for Cross-Database Parkinson’s Disease Detection and Speech Features Extraction

Original language description

Advancements in deep learning speech representations have facilitated the effective use of extensive unlabeled speech datasets for Parkinson’s disease (PD) modeling with minimal annotated data. This study employs the non-fine-tuned wav2vec 1.0 architecture to develop machine learning models for PD speech diagnosis tasks, such as cross-database classification and regression to predict demographic and articulation characteristics. The primary aim is to analyze overlapping components within the embeddings on both classification and regression tasks, investigating whether latent speech representations in PD are shared across models, particularly for related tasks. Firstly, evaluation using three multi-language PD datasets showed that wav2vec accurately detected PD based on speech, outperforming feature extraction using mel-frequency cepstral coefficients in the proposed cross-database classification scenarios. In cross-database scenarios using Italian and English-read texts, wav2vec demonstrated performance comparable to intra-dataset evaluations. We also compared our cross-database findings against those of other related studies. Secondly, wav2vec proved effective in regression, modeling various quantitative speech characteristics related to articulation and aging. Ultimately, subsequent analysis of important features examined the presence of significant overlaps between classification and regression models. The feature importance experiments discovered shared features across trained models, with increased sharing for related tasks, further suggesting that wav2vec contributes to improved generalizability. The study proposes wav2vec embeddings as a next promising step toward a speech-based universal model to assist in the evaluation of PD.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20601 - Medical engineering

Project

<a href="/en/project/LX22NPO5107" target="_blank" >LX22NPO5107: National institute for Neurological Research</a><br>

Continuities

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

Publication year

2024

Confidentiality

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

Name of the periodical

Sensors

ISSN

1424-8220

e-ISSN

1424-8220

Volume of the periodical

24

Issue of the periodical within the volume

17

Country of publishing house

CH - SWITZERLAND

Number of pages

22

Pages from-to

1-22

UT code for WoS article

001311558300001

EID of the result in the Scopus database

2-s2.0-85203878761