<?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-03979667</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="2026-05-02T11:43:06+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">From HEAR to GEAR: Generative Evaluation of Audio Representations</title>
            <author role="crp">
              <persName>
                <forename type="first">Vincent</forename>
                <surname>Lostanlen</surname>
              </persName>
              <email type="md5">fb6df559aa5c29ab76c527cfa88f7fc0</email>
              <email type="domain">ens.fr</email>
              <idno type="idhal" notation="string">lostanlen</idno>
              <idno type="idhal" notation="numeric">749246</idno>
              <idno type="halauthorid" notation="string">22295-749246</idno>
              <idno type="ARXIV">https://arxiv.org/a/lostanlen_v_1</idno>
              <idno type="IDREF">https://www.idref.fr/203022769</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0580-1651</idno>
              <idno type="VIAF">https://viaf.org/viaf/77150565679606251603</idno>
              <affiliation ref="#struct-1088564"/>
              <affiliation ref="#struct-1088571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Lingyao</forename>
                <surname>Yan</surname>
              </persName>
              <email type="md5">9193e3191f1c98924285395b4c15ef1e</email>
              <email type="domain">buaa.edu.cn</email>
              <idno type="idhal" notation="numeric">1225128</idno>
              <idno type="halauthorid" notation="string">2718695-1225128</idno>
              <affiliation ref="#struct-446139"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xianyi</forename>
                <surname>Yang</surname>
              </persName>
              <email type="md5">6b75b0fbae4086794dbb1da67aea7700</email>
              <email type="domain">buaa.edu.cn</email>
              <idno type="idhal" notation="numeric">1225129</idno>
              <idno type="halauthorid" notation="string">2718696-1225129</idno>
              <affiliation ref="#struct-446139"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Vincent</forename>
                <surname>Lostanlen</surname>
              </persName>
              <email type="md5">2f39ccbbd1581982210556806407adee</email>
              <email type="domain">ls2n.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-02-08 20:32:50</date>
              <date type="whenModified">2026-01-19 16:46:21</date>
              <date type="whenReleased">2023-02-09 14:46:34</date>
              <date type="whenProduced">2023-02-08</date>
              <date type="whenEndEmbargoed">2023-02-08</date>
              <ref type="file" target="https://hal.science/hal-03979667v1/document">
                <date notBefore="2023-02-08"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-03979667v1/file/lostanlen2022hear.pdf" id="file-3979667-3472728">
                <date notBefore="2023-02-08"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="832101">
                <persName>
                  <forename>Vincent</forename>
                  <surname>Lostanlen</surname>
                </persName>
                <email type="md5">2f39ccbbd1581982210556806407adee</email>
                <email type="domain">ls2n.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03979667</idno>
            <idno type="halUri">https://hal.science/hal-03979667</idno>
            <idno type="halBibtex">lostanlen:hal-03979667</idno>
            <idno type="halRefHtml">&lt;i&gt;Proceedings of Machine Learning Research&lt;/i&gt;, 2023, 166, pp.48-64</idno>
            <idno type="halRef">Proceedings of Machine Learning Research, 2023, 166, pp.48-64</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3979667-3472728"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="EC-NANTES">Ecole Centrale de Nantes</idno>
            <idno type="stamp" n="UNAM">l'unam - université nantes angers le mans</idno>
            <idno type="stamp" n="LS2N">Laboratoire des Sciences du Numérique de Nantes</idno>
            <idno type="stamp" n="LS2N-SIMS" corresp="LS2N">LS2N - équipe SIMS ( Signal, IMage et Son )</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="NANTES-UNIVERSITE">Nantes Université</idno>
            <idno type="stamp" n="NANTES-UNIV">Nantes Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">From HEAR to GEAR: Generative Evaluation of Audio Representations</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Vincent</forename>
                    <surname>Lostanlen</surname>
                  </persName>
                  <email type="md5">fb6df559aa5c29ab76c527cfa88f7fc0</email>
                  <email type="domain">ens.fr</email>
                  <idno type="idhal" notation="string">lostanlen</idno>
                  <idno type="idhal" notation="numeric">749246</idno>
                  <idno type="halauthorid" notation="string">22295-749246</idno>
                  <idno type="ARXIV">https://arxiv.org/a/lostanlen_v_1</idno>
                  <idno type="IDREF">https://www.idref.fr/203022769</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0580-1651</idno>
                  <idno type="VIAF">https://viaf.org/viaf/77150565679606251603</idno>
                  <affiliation ref="#struct-1088564"/>
                  <affiliation ref="#struct-1088571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Lingyao</forename>
                    <surname>Yan</surname>
                  </persName>
                  <email type="md5">9193e3191f1c98924285395b4c15ef1e</email>
                  <email type="domain">buaa.edu.cn</email>
                  <idno type="idhal" notation="numeric">1225128</idno>
                  <idno type="halauthorid" notation="string">2718695-1225128</idno>
                  <affiliation ref="#struct-446139"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xianyi</forename>
                    <surname>Yang</surname>
                  </persName>
                  <email type="md5">6b75b0fbae4086794dbb1da67aea7700</email>
                  <email type="domain">buaa.edu.cn</email>
                  <idno type="idhal" notation="numeric">1225129</idno>
                  <idno type="halauthorid" notation="string">2718696-1225129</idno>
                  <affiliation ref="#struct-446139"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">117525</idno>
                <idno type="issn">1938-7228</idno>
                <idno type="eissn">2640-3498</idno>
                <title level="j">Proceedings of Machine Learning Research</title>
                <imprint>
                  <publisher>PMLR</publisher>
                  <biblScope unit="issue">166</biblScope>
                  <biblScope unit="pp">48-64</biblScope>
                  <date type="datePub">2023-02-08</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-sd">Computer Science [cs]/Sound [cs.SD]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The "Holistic Evaluation of Audio Representations" (HEAR) is an emerging research program towards statistical models that can transfer to diverse machine listening tasks. The originality of HEAR is to conduct a fair, "apples-to-apples" comparison of many deep learning models over many datasets, resulting in multitask evaluation metrics that are readily interpretable by practitioners. On the flip side, this comparison incurs a neural architecture search: as such, it is not directly interpretable in terms of audio signal processing. In this paper, we propose a complementary viewpoint on the HEAR benchmark, which we name GEAR: Generative Evaluation of Audio Representations. The key idea behind GEAR is to generate a dataset of sounds with few independent factors of variability, analyze it with HEAR embeddings, and visualize it with an unsupervised manifold learning algorithm. Visual inspection reveals stark contrasts in the global structure of the nearest-neighbor graphs associated to logmelspec, Open-L 3 , BYOL, CREPE, wav2vec2, GURA, and YAMNet. Although GEAR currently lacks mathematical refinement, we intend it as a proof of concept to show the potential of parametric audio synthesis in general-purpose machine listening research.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1088564" status="VALID">
          <idno type="IdRef">203637585</idno>
          <idno type="RNSR">201722241F</idno>
          <idno type="ROR">https://ror.org/02snf8m58</idno>
          <orgName>Laboratoire des Sciences du Numérique de Nantes</orgName>
          <orgName type="acronym">LS2N</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>Nantes Université – faculté des Sciences et Techniques (FST)2 Chemin de la HoussinièreBP 92208, 44322 Nantes Cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ls2n.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR6004" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-1086798" type="direct"/>
            <relation active="#struct-1083366" type="indirect"/>
            <relation active="#struct-1088543" type="direct"/>
            <relation active="#struct-1083400" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1088571" status="VALID">
          <orgName>Signal, IMage et Son</orgName>
          <orgName type="acronym">LS2N - équipe SIMS</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1088564" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR6004" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-1086798" type="indirect"/>
            <relation active="#struct-1083366" type="indirect"/>
            <relation active="#struct-1088543" type="indirect"/>
            <relation active="#struct-1083400" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-446139" status="INCOMING">
          <orgName>Sino-French Engineer School, Beihang University</orgName>
          <desc>
            <address>
              <country key="CN"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</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>
        <org type="institution" xml:id="struct-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1086798" status="VALID">
          <idno type="IdRef">03063525X</idno>
          <idno type="ISNI">0000000122039289</idno>
          <idno type="ROR">https://ror.org/03nh7d505</idno>
          <orgName>NANTES UNIVERSITÉ - École Centrale de Nantes</orgName>
          <orgName type="acronym">Nantes Univ - ECN</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>1 rue de la Noë - BP 92101 - 44321 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083366" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1083366" status="VALID">
          <idno type="IdRef">258086599</idno>
          <idno type="ROR">https://ror.org/03gnr7b55</idno>
          <orgName>Nantes Université</orgName>
          <orgName type="acronym">Nantes Univ</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1088543" status="VALID">
          <orgName>Nantes université - UFR des Sciences et des Techniques</orgName>
          <orgName type="acronym">Nantes univ -  UFR ST</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>2, rue de la Houssinière - BP 92208 - 44322 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sciences-techniques.univ-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083400" type="direct"/>
            <relation active="#struct-1083366" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1083400" status="VALID">
          <orgName>Nantes Université - pôle Sciences et technologie</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://nouvelleuniversite.univ-nantes.fr/les-poles</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083366" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>