<?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-04675781</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="2026-05-03T09:10:50+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">STONE: Self-supervised Tonality Estimator</title>
            <author role="aut">
              <persName>
                <forename type="first">Yuexuan</forename>
                <surname>Kong</surname>
              </persName>
              <email type="md5">203b02a0fa8378d363ac1b2e2d1a2a70</email>
              <email type="domain">deezer.com</email>
              <idno type="idhal" notation="numeric">1408959</idno>
              <idno type="halauthorid" notation="string">3217514-1408959</idno>
              <affiliation ref="#struct-1040468"/>
              <affiliation ref="#struct-1088564"/>
            </author>
            <author role="aut">
              <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">Gabriel</forename>
                <surname>Meseguer-Brocal</surname>
              </persName>
              <email type="md5">c4f9a21d7ca6b37bef505f189537a9b8</email>
              <email type="domain">ircam.fr</email>
              <idno type="idhal" notation="numeric">1042752</idno>
              <idno type="halauthorid" notation="string">1224378-1042752</idno>
              <affiliation ref="#struct-1040468"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Stella</forename>
                <surname>Wong</surname>
              </persName>
              <idno type="halauthorid">3217515-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mathieu</forename>
                <surname>Lagrange</surname>
              </persName>
              <email type="md5">ac100a13668078efbd012f54e6ef9b7d</email>
              <email type="domain">ls2n.fr</email>
              <idno type="idhal" notation="string">mathieu-lagrange</idno>
              <idno type="idhal" notation="numeric">4329</idno>
              <idno type="halauthorid" notation="string">120625-4329</idno>
              <affiliation ref="#struct-1088564"/>
              <affiliation ref="#struct-1088571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>Hennequin</surname>
              </persName>
              <email type="md5">b7fc343f33a1ad05791045a038b7e5b6</email>
              <email type="domain">deezer.com</email>
              <idno type="idhal" notation="numeric">1016644</idno>
              <idno type="halauthorid" notation="string">518908-1016644</idno>
              <affiliation ref="#struct-1040468"/>
            </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">2024-08-22 18:04:34</date>
              <date type="whenModified">2026-01-19 16:46:21</date>
              <date type="whenReleased">2024-08-23 13:43:08</date>
              <date type="whenProduced">2024-11-10</date>
              <date type="whenEndEmbargoed">2024-08-22</date>
              <ref type="file" target="https://hal.science/hal-04675781v1/document">
                <date notBefore="2024-08-22"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04675781v1/file/STONE___ISMIR_2024.pdf" id="file-4675781-4063234">
                <date notBefore="2024-08-22"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2407.07408"/>
            </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-04675781</idno>
            <idno type="halUri">https://hal.science/hal-04675781</idno>
            <idno type="halBibtex">kong:hal-04675781</idno>
            <idno type="halRefHtml">&lt;i&gt;International Society for Music Information Retrieval Conference (ISMIR)&lt;/i&gt;, Nov 2024, San Francisco, United States</idno>
            <idno type="halRef">International Society for Music Information Retrieval Conference (ISMIR), Nov 2024, San Francisco, United States</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4675781-4063234"/></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="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">STONE: Self-supervised Tonality Estimator</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Yuexuan</forename>
                    <surname>Kong</surname>
                  </persName>
                  <email type="md5">203b02a0fa8378d363ac1b2e2d1a2a70</email>
                  <email type="domain">deezer.com</email>
                  <idno type="idhal" notation="numeric">1408959</idno>
                  <idno type="halauthorid" notation="string">3217514-1408959</idno>
                  <affiliation ref="#struct-1040468"/>
                  <affiliation ref="#struct-1088564"/>
                </author>
                <author role="aut">
                  <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">Gabriel</forename>
                    <surname>Meseguer-Brocal</surname>
                  </persName>
                  <email type="md5">c4f9a21d7ca6b37bef505f189537a9b8</email>
                  <email type="domain">ircam.fr</email>
                  <idno type="idhal" notation="numeric">1042752</idno>
                  <idno type="halauthorid" notation="string">1224378-1042752</idno>
                  <affiliation ref="#struct-1040468"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Stella</forename>
                    <surname>Wong</surname>
                  </persName>
                  <idno type="halauthorid">3217515-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mathieu</forename>
                    <surname>Lagrange</surname>
                  </persName>
                  <email type="md5">ac100a13668078efbd012f54e6ef9b7d</email>
                  <email type="domain">ls2n.fr</email>
                  <idno type="idhal" notation="string">mathieu-lagrange</idno>
                  <idno type="idhal" notation="numeric">4329</idno>
                  <idno type="halauthorid" notation="string">120625-4329</idno>
                  <affiliation ref="#struct-1088564"/>
                  <affiliation ref="#struct-1088571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>Hennequin</surname>
                  </persName>
                  <email type="md5">b7fc343f33a1ad05791045a038b7e5b6</email>
                  <email type="domain">deezer.com</email>
                  <idno type="idhal" notation="numeric">1016644</idno>
                  <idno type="halauthorid" notation="string">518908-1016644</idno>
                  <affiliation ref="#struct-1040468"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)</title>
                <meeting>
                  <title>International Society for Music Information Retrieval Conference (ISMIR)</title>
                  <date type="start">2024-11-10</date>
                  <date type="end">2024-11-14</date>
                  <settlement>San Francisco</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint/>
              </monogr>
              <idno type="arxiv">2407.07408</idno>
            </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="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</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>Although deep neural networks can estimate the key of a musical piece, their supervision incurs a massive annotation effort. Against this shortcoming, we present STONE, the first self-supervised tonality estimator. The architecture behind STONE, named ChromaNet, is a convnet with octave equivalence which outputs a "key signature profile" (KSP) of 12 structured logits. First, we train ChromaNet to regress artificial pitch transpositions between any two unlabeled musical excerpts from the same audio track, as measured as cross-power spectral density (CPSD) within the circle of fifths (CoF). We observe that this self-supervised pretext task leads KSP to correlate with tonal key signature. Based on this observation, we extend STONE to output a structured KSP of 24 logits, and introduce supervision so as to disambiguate major versus minor keys sharing the same key signature. Applying different amounts of supervision yields semi-supervised and fully supervised tonality estimators: i.e., Semi-TONEs and Sup-TONEs. We evaluate these estimators on FMAK, a new dataset of 5489 real-world musical recordings with expert annotation of 24 major and minor keys. We find that Semi-TONE matches the classification accuracy of Sup-TONE with reduced supervision and outperforms it with equal supervision.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1040468" status="VALID">
          <orgName>Deezer Research</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://research.deezer.com/projects/</ref>
          </desc>
        </org>
        <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-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>