<?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-02653051</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="2026-05-14T22:36:51+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A musically motivated mid-level representation for pitch estimation and musical audio source separation</title>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Louis</forename>
                <surname>Durrieu</surname>
              </persName>
              <idno type="halauthorid">528125-0</idno>
              <affiliation ref="#struct-162010"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Bertrand</forename>
                <surname>David</surname>
              </persName>
              <email type="md5">c66e48ef0efbef7d145f57db8e67b0e9</email>
              <email type="domain">enst.fr</email>
              <idno type="idhal" notation="string">bedavid</idno>
              <idno type="idhal" notation="numeric">179908</idno>
              <idno type="halauthorid" notation="string">23936-179908</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1153-422X</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gael</forename>
                <surname>Richard</surname>
              </persName>
              <email type="md5">c0a23dcedaef8bf8b03c039e9418997d</email>
              <email type="domain">telecom-paris.fr</email>
              <idno type="idhal" notation="string">gael-richard</idno>
              <idno type="idhal" notation="numeric">14146</idno>
              <idno type="halauthorid" notation="string">22606-14146</idno>
              <idno type="IDREF">https://www.idref.fr/094977208</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4960-0010</idno>
              <affiliation ref="#struct-554452"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gaël</forename>
                <surname>RICHARD</surname>
              </persName>
              <email type="md5">c0a23dcedaef8bf8b03c039e9418997d</email>
              <email type="domain">telecom-paris.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-05-29 20:31:14</date>
              <date type="whenModified">2026-02-07 05:19:14</date>
              <date type="whenReleased">2020-06-03 10:31:22</date>
              <date type="whenProduced">2011-10</date>
              <date type="whenEndEmbargoed">2020-05-29</date>
              <ref type="file" target="https://hal.science/hal-02653051v1/document">
                <date notBefore="2020-05-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02653051v1/file/JSTSP11_Durrieu.pdf" id="file-2653051-2469101">
                <date notBefore="2020-05-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="534316">
                <persName>
                  <forename>Gaël</forename>
                  <surname>RICHARD</surname>
                </persName>
                <email type="md5">c0a23dcedaef8bf8b03c039e9418997d</email>
                <email type="domain">telecom-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02653051</idno>
            <idno type="halUri">https://hal.science/hal-02653051</idno>
            <idno type="halBibtex">durrieu:hal-02653051</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Journal on Selected Topics in Signal Processing&lt;/i&gt;, 2011</idno>
            <idno type="halRef">IEEE Journal on Selected Topics in Signal Processing, 2011</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2653051-2469101"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="ENST">Ecole Nationale Supérieure des Télécommunications</idno>
            <idno type="stamp" n="TELECOM-PARISTECH" corresp="PARISTECH">Télécom Paris</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="LTCI" corresp="TELECOM-PARISTECH">Laboratoire Traitement et Communication de l'Information</idno>
            <idno type="stamp" n="IDS" corresp="TELECOM-PARISTECH">Département Image, Données, Signal</idno>
            <idno type="stamp" n="S2A" corresp="TELECOM-PARISTECH">Equipe Signal, Statistique et Apprentissage</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</idno>
            <idno type="stamp" n="DEPARTEMENT-DE-MATHEMATIQUES">Collection du Département de Mathématiques</idno>
            <idno type="stamp" n="IP-PARIS-DEPARTEMENT-MATHEMATIQUES">Département de Mathèmatiques</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">A musically motivated mid-level representation for pitch estimation and musical audio source separation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Louis</forename>
                    <surname>Durrieu</surname>
                  </persName>
                  <idno type="halauthorid">528125-0</idno>
                  <affiliation ref="#struct-162010"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Bertrand</forename>
                    <surname>David</surname>
                  </persName>
                  <email type="md5">c66e48ef0efbef7d145f57db8e67b0e9</email>
                  <email type="domain">enst.fr</email>
                  <idno type="idhal" notation="string">bedavid</idno>
                  <idno type="idhal" notation="numeric">179908</idno>
                  <idno type="halauthorid" notation="string">23936-179908</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1153-422X</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gael</forename>
                    <surname>Richard</surname>
                  </persName>
                  <email type="md5">c0a23dcedaef8bf8b03c039e9418997d</email>
                  <email type="domain">telecom-paris.fr</email>
                  <idno type="idhal" notation="string">gael-richard</idno>
                  <idno type="idhal" notation="numeric">14146</idno>
                  <idno type="halauthorid" notation="string">22606-14146</idno>
                  <idno type="IDREF">https://www.idref.fr/094977208</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4960-0010</idno>
                  <affiliation ref="#struct-554452"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="INCOMING">155753</idno>
                <title level="j">IEEE Journal on Selected Topics in Signal Processing</title>
                <imprint>
                  <date type="datePub">2011-10</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Index Terms-Non-negative Matrix Factorization (NMF)</term>
                <term xml:lang="en">au- dio signal representation</term>
                <term xml:lang="en">pitch estimation</term>
                <term xml:lang="en">audio melody extrac- tion</term>
                <term xml:lang="en">musical audio source separation</term>
              </keywords>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</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>When designing an audio processing system, the target tasks often influence the choice of a data representation or transformation. Low-level time-frequency representations such as the short-time Fourier transform (STFT) are popular, because they offer a meaningful insight on sound properties for a low computational cost. Conversely, when higher level semantics, such as pitch, timbre or phoneme, are sought after, representations usually tend to enhance their discriminative characteristics, at the expense of their invertibility. They become so-called mid-level representations. In this paper, a source/filter signal model which provides a mid-level representation is proposed. This representation makes the pitch content of the signal as well as some timbre information available, hence keeping as much information from the raw data as possible. This model is successfully used within a main melody extraction system and a lead instrument/accompaniment separation system. Both frameworks obtained top results at several international evaluation campaigns.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-162010" status="OLD">
          <orgName>Laboratoire Traitement et Communication de l'Information</orgName>
          <orgName type="acronym">LTCI</orgName>
          <desc>
            <address>
              <addrLine>46 rue Barrault F-75634 Paris Cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ltci.telecom-paristech.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300362" type="direct"/>
            <relation active="#struct-302102" type="direct"/>
            <relation name="UMR5141" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-554452" status="VALID">
          <orgName>Signal, Statistique et Apprentissage</orgName>
          <orgName type="acronym">S2A</orgName>
          <date type="start">2019-02-22</date>
          <desc>
            <address>
              <addrLine>Télécom Paris 19 Place Marguerite Perey 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr/fr/recherche/laboratoires/laboratoire-traitement-et-communication-de-linformation-ltci/les-equipes-de-recherche/signal-statistique-et-apprentissage-s2a</ref>
          </desc>
          <listRelation>
            <relation active="#struct-484335" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-1048346" type="indirect"/>
            <relation active="#struct-563936" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300362" status="VALID">
          <idno type="ROR">https://ror.org/01naq7912</idno>
          <orgName>Télécom ParisTech</orgName>
          <date type="start">2008-01-01</date>
          <date type="end">2019-06-11</date>
          <desc>
            <address>
              <addrLine>46 rue Barrault 75634 Paris Cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr</ref>
          </desc>
        </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="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="laboratory" xml:id="struct-484335" status="VALID">
          <idno type="IdRef">162384270</idno>
          <idno type="ISNI">0000 0000 9194 9502</idno>
          <idno type="RNSR">200319327Z</idno>
          <idno type="ROR">https://ror.org/057er4c39</idno>
          <orgName>Laboratoire Traitement et Communication de l'Information</orgName>
          <orgName type="acronym">LTCI</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Télécom Paris 19 Place Marguerite Perey 91120 PALAISEAU</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr/fr/recherche/laboratoires/laboratoire-traitement-et-communication-de-linformation-ltci</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
            <relation active="#struct-1048346" type="direct"/>
            <relation active="#struct-563936" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1048346" status="VALID">
          <idno type="IdRef">026375273</idno>
          <idno type="ISNI">0000 0001 2108 2779</idno>
          <idno type="ROR">https://ror.org/01naq7912</idno>
          <orgName>Télécom Paris</orgName>
          <date type="start">2019-06-12</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
            <relation active="#struct-563936" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-563936" status="VALID">
          <idno type="IdRef">238327159</idno>
          <idno type="ISNI">0000000502717600</idno>
          <idno type="ROR">https://ror.org/042tfbd02</idno>
          <idno type="Wikidata">Q48759778</idno>
          <orgName>Institut Polytechnique de Paris</orgName>
          <orgName type="acronym">IP Paris</orgName>
          <date type="start">2019-06-02</date>
          <desc>
            <address>
              <addrLine>Route de Saclay, 91120 Palaiseau Cedex, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ip-paris.fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>