<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04683361</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-25T10:00:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Transfer Learning from Whisper for Microscopic Intelligibility Prediction</title>
            <author role="aut">
              <persName>
                <forename type="first">Paul</forename>
                <surname>Best</surname>
              </persName>
              <idno type="halauthorid">1382726-0</idno>
              <affiliation ref="#struct-530702"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Santiago</forename>
                <surname>Cuervo</surname>
              </persName>
              <idno type="halauthorid">2618424-0</idno>
              <affiliation ref="#struct-530702"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ricard</forename>
                <surname>Marxer</surname>
              </persName>
              <email type="md5">5acbab6a8b091e3c949098a46a2ba92b</email>
              <email type="domain">univ-tln.fr</email>
              <idno type="idhal" notation="string">ricard-marxer</idno>
              <idno type="idhal" notation="numeric">19391</idno>
              <idno type="halauthorid" notation="string">27165-19391</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5099-5059</idno>
              <idno type="IDREF">https://www.idref.fr/240437713</idno>
              <affiliation ref="#struct-530702"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Ricard</forename>
                <surname>Marxer</surname>
              </persName>
              <email type="md5">5acbab6a8b091e3c949098a46a2ba92b</email>
              <email type="domain">univ-tln.fr</email>
            </editor>
            <funder ref="#projanr-52222"/>
            <funder ref="#projanr-42476"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-09-04 08:26:50</date>
              <date type="whenModified">2026-04-23 03:08:53</date>
              <date type="whenReleased">2024-09-05 16:08:32</date>
              <date type="whenProduced">2024-09-01</date>
              <date type="whenEndEmbargoed">2024-09-04</date>
              <ref type="file" target="https://hal.science/hal-04683361v1/document">
                <date notBefore="2024-09-04"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04683361v1/file/best24_interspeech.pdf" id="file-4686530-4076266">
                <date notBefore="2024-09-04"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2404.01737"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="578772">
                <persName>
                  <forename>Ricard</forename>
                  <surname>Marxer</surname>
                </persName>
                <email type="md5">5acbab6a8b091e3c949098a46a2ba92b</email>
                <email type="domain">univ-tln.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04683361</idno>
            <idno type="halUri">https://hal.science/hal-04683361</idno>
            <idno type="halBibtex">best:hal-04683361</idno>
            <idno type="halRefHtml">&lt;i&gt;Interspeech 2024&lt;/i&gt;, Sep 2024, Kos, Greece. pp.3839-3843, &lt;a target="_blank" href="https://dx.doi.org/10.21437/Interspeech.2024-2258"&gt;&amp;#x27E8;10.21437/Interspeech.2024-2258&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Interspeech 2024, Sep 2024, Kos, Greece. pp.3839-3843, &amp;#x27E8;10.21437/Interspeech.2024-2258&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4686530-4076266"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLN">Université de Toulon</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-AMU">Aix Marseille Université</idno>
            <idno type="stamp" n="ILCB">Institut Langage, Communication et Cerveau</idno>
            <idno type="stamp" n="LIS-LAB">Laboratoire d'Informatique et Systèmes</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ANR-IA-20" corresp="ANR-IA">ANR-IA-20</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Transfer Learning from Whisper for Microscopic Intelligibility Prediction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Paul</forename>
                    <surname>Best</surname>
                  </persName>
                  <idno type="halauthorid">1382726-0</idno>
                  <affiliation ref="#struct-530702"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Santiago</forename>
                    <surname>Cuervo</surname>
                  </persName>
                  <idno type="halauthorid">2618424-0</idno>
                  <affiliation ref="#struct-530702"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ricard</forename>
                    <surname>Marxer</surname>
                  </persName>
                  <email type="md5">5acbab6a8b091e3c949098a46a2ba92b</email>
                  <email type="domain">univ-tln.fr</email>
                  <idno type="idhal" notation="string">ricard-marxer</idno>
                  <idno type="idhal" notation="numeric">19391</idno>
                  <idno type="halauthorid" notation="string">27165-19391</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5099-5059</idno>
                  <idno type="IDREF">https://www.idref.fr/240437713</idno>
                  <affiliation ref="#struct-530702"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Interspeech 2024</title>
                  <date type="start">2024-09-01</date>
                  <date type="end">2024-09-05</date>
                  <settlement>Kos</settlement>
                  <country key="GR">Greece</country>
                </meeting>
                <imprint>
                  <publisher>ISCA</publisher>
                  <biblScope unit="serie">Interspeech 2024</biblScope>
                  <biblScope unit="pp">3839-3843</biblScope>
                </imprint>
              </monogr>
              <idno type="arxiv">2404.01737</idno>
              <idno type="doi">10.21437/Interspeech.2024-2258</idno>
              <ref type="publisher">https://interspeech2024.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">speech perception</term>
                <term xml:lang="en">intelligibility prediction</term>
                <term xml:lang="en">Whisper</term>
                <term xml:lang="en">deep learning</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-sd">Computer Science [cs]/Sound [cs.SD]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Macroscopic intelligibility models predict the expected human word-error-rate for a given speech-in-noise stimulus. In contrast, microscopic intelligibility models aim to make fine-grained predictions about listeners' perception, e.g. predicting phonetic or lexical responses. State-of-the-art macroscopic models use transfer learning from large scale deep learning models for speech processing, whereas such methods have rarely been used for microscopic modeling. In this paper, we study the use of transfer learning from Whisper, a state-of-the-art deep learning model for automatic speech recognition, for microscopic intelligibility prediction at the level of lexical responses. Our method outperforms the considered baselines, even in a zero-shot setup, and yields a relative improvement of up to 66% when fine-tuned to predict listeners' responses. Our results showcase the promise of large scale deep learning based methods for microscopic intelligibility prediction.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-530702" status="VALID">
          <orgName>DYNamiques de l’Information</orgName>
          <orgName type="acronym">DYNI</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lis-lab.fr/dyni</ref>
          </desc>
          <listRelation>
            <relation active="#struct-527033" type="direct"/>
            <relation name="UMR7020" active="#struct-198056" type="indirect"/>
            <relation name="UMR7020" active="#struct-303091" type="indirect"/>
            <relation name="UMR7020" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-527033" status="VALID">
          <idno type="IdRef">234768002</idno>
          <idno type="RNSR">201822714R</idno>
          <idno type="ROR">https://ror.org/0257sgk90</idno>
          <idno type="Wikidata">Q52605252</idno>
          <orgName>Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon)</orgName>
          <orgName type="acronym">LIS</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Aix Marseille Université – Campus de Saint Jérôme – Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lis-lab.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR7020" active="#struct-198056" type="direct"/>
            <relation name="UMR7020" active="#struct-303091" type="direct"/>
            <relation name="UMR7020" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-198056" status="VALID">
          <idno type="IdRef">15863621X</idno>
          <idno type="ISNI">0000 0001 2176 4817</idno>
          <idno type="ROR">https://ror.org/035xkbk20</idno>
          <orgName>Aix Marseille Université</orgName>
          <orgName type="acronym">AMU</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Aix-Marseille UniversitéJardins du Pharo58 Boulevard Charles Livon13284 Marseille cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-amu.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303091" status="VALID">
          <idno type="IdRef">031122337</idno>
          <idno type="ROR">https://ror.org/02m9kbe37</idno>
          <orgName>Université de Toulon</orgName>
          <orgName type="acronym">UTLN</orgName>
          <desc>
            <address>
              <addrLine>Avenue de l'Université - BP 20132 - 83957 La Garde Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tln.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-52222" status="VALID">
          <idno type="anr">ANR-20-CE23-0012</idno>
          <orgName>MIM</orgName>
          <desc>Modelisation Microscopique de l'Intelligibilité</desc>
          <date type="start">2020</date>
        </org>
        <org type="anrProject" xml:id="projanr-42476" status="VALID">
          <idno type="anr">ANR-16-CONV-0002</idno>
          <orgName>ILCB</orgName>
          <desc>ILCB: Institute of Language Communication and the Brain</desc>
          <date type="start">2016</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>