<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3823</id>
    <completedYear>2024</completedYear>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">It’s Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinson’s Disease</title>
    <abstract language="eng">Pre-trained models generate speech representations that are used in different tasks, including the automatic detection of Parkinson’s disease (PD). Although these models can yield high accuracy, their interpretation is still challenging. This paper used a pre-trained Wav2vec 2.0 model to represent speech frames of 25ms length and perform a frame-by-frame discrimination between PD patients and healthy control (HC) subjects. This fine granularity prediction enabled us to identify specific linguistic segments with high discrimination capability. Speech representations of all produced verbs were compared&#13;
w.r.t. nouns and the first ones yielded higher accuracies. To gaina deeper &#13;
 understanding of this pattern, representations of motor and non-motor verbs were compared and the first ones yielded better results, with accuracies of around 83% in an independent test set. These findings support well-established neurocognitive models about action-related language highlighted as key drivers of PD. Index Terms: computational paralinguistics, interpretability of pre-trained models, action verbs, Parkinson’s disease</abstract>
    <identifier type="doi">10.21437/Interspeech.2024-2205</identifier>
    <enrichment key="opus_doi_flag">false</enrichment>
    <enrichment key="opus_import_data">&lt;div class="errorPage"&gt;    &lt;h2&gt;Application error&lt;/h2&gt;        &lt;div class="exceptionMessage"&gt;        Invalid URI supplied    &lt;/div&gt;        &lt;/div&gt;</enrichment>
    <enrichment key="conference_title">Interspeech 2024</enrichment>
    <enrichment key="conference_place">Kos, Greece</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <author>Daniel Escobar-Grisales</author>
    <author>Cristian-David Ríos-Urrego</author>
    <author>Ilja Baumann</author>
    <author>Korbinian Riedhammer</author>
    <author>Elmar Nöth</author>
    <author>Tobias Bocklet</author>
    <author>Adolfo Garcia</author>
    <author>Juan rafael Orozco-Arroyave</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>computational paralinguistics, interpretability of pre-trained models, action verbs, Parkinson’s disease</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
    <collection role="Forschungsschwerpunkt" number="5">Digitalisierung &amp; Künstliche Intelligenz</collection>
    <collection role="institutes" number="">Zentrum für Künstliche Intelligenz (KIZ)</collection>
  </doc>
</export-example>
