<?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-01161322</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="2026-05-15T17:01:10+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Toward Automatic Music Audio Summary Generation from Signal Analysis</title>
            <author role="aut">
              <persName>
                <forename type="first">Geoffroy</forename>
                <surname>Peeters</surname>
              </persName>
              <email type="md5">6a8a5918e2bef465791fcef124f5bfdd</email>
              <email type="domain">telecom-paris.fr</email>
              <idno type="idhal" notation="string">geoffroy-peeters</idno>
              <idno type="idhal" notation="numeric">6738</idno>
              <idno type="halauthorid" notation="string">11190-6738</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5255-3019</idno>
              <idno type="IDREF">https://www.idref.fr/187470472</idno>
              <affiliation ref="#struct-410616"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Amaury</forename>
                <surname>La Burthe</surname>
              </persName>
              <idno type="halauthorid">841803-0</idno>
              <affiliation ref="#struct-410616"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xavier</forename>
                <surname>Rodet</surname>
              </persName>
              <idno type="halauthorid">317388-0</idno>
              <affiliation ref="#struct-410616"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>ircam</forename>
                <surname>ircam</surname>
              </persName>
              <email type="md5">940422a1784042e68271c0065710df37</email>
              <email type="domain">ircam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-06-08 14:35:59</date>
              <date type="whenModified">2023-03-24 14:53:00</date>
              <date type="whenReleased">2015-06-08 16:55:50</date>
              <date type="whenProduced">2002-10</date>
              <date type="whenEndEmbargoed">2015-06-08</date>
              <ref type="file" target="https://hal.science/hal-01161322v1/document">
                <date notBefore="2015-06-08"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01161322v1/file/index.pdf" id="file-1161322-1245077">
                <date notBefore="2015-06-08"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="306805">
                <persName>
                  <forename>ircam</forename>
                  <surname>ircam</surname>
                </persName>
                <email type="md5">940422a1784042e68271c0065710df37</email>
                <email type="domain">ircam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01161322</idno>
            <idno type="halUri">https://hal.science/hal-01161322</idno>
            <idno type="halBibtex">peeters:hal-01161322</idno>
            <idno type="halRefHtml">&lt;i&gt;ISMIR&lt;/i&gt;, Oct 2002, Paris, France. pp.1-1</idno>
            <idno type="halRef">ISMIR, Oct 2002, Paris, France. pp.1-1</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1161322-1245077"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UPMC" corresp="SORBONNE-UNIVERSITE">Université Pierre et Marie Curie</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="IRCAM">Institut de Recherche et Coordination Acoustique/Musique</idno>
            <idno type="stamp" n="STMS" corresp="SORBONNE-UNIVERSITE">Sciences et technologies de la musique et du son</idno>
            <idno type="stamp" n="UPMC_POLE_1" corresp="UPMC">UPMC Pôle 1</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">                            cote interne IRCAM: Peeters02c</note>
            <note type="description">None / None</note>
            <note type="audience" n="3">National</note>
            <note type="invited" n="1">Yes</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="0">No</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Toward Automatic Music Audio Summary Generation from Signal Analysis</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Geoffroy</forename>
                    <surname>Peeters</surname>
                  </persName>
                  <email type="md5">6a8a5918e2bef465791fcef124f5bfdd</email>
                  <email type="domain">telecom-paris.fr</email>
                  <idno type="idhal" notation="string">geoffroy-peeters</idno>
                  <idno type="idhal" notation="numeric">6738</idno>
                  <idno type="halauthorid" notation="string">11190-6738</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5255-3019</idno>
                  <idno type="IDREF">https://www.idref.fr/187470472</idno>
                  <affiliation ref="#struct-410616"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Amaury</forename>
                    <surname>La Burthe</surname>
                  </persName>
                  <idno type="halauthorid">841803-0</idno>
                  <affiliation ref="#struct-410616"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xavier</forename>
                    <surname>Rodet</surname>
                  </persName>
                  <idno type="halauthorid">317388-0</idno>
                  <affiliation ref="#struct-410616"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">ISMIR</title>
                <meeting>
                  <title>ISMIR</title>
                  <date type="start">2002-10</date>
                  <settlement>Paris</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">1-1</biblScope>
                  <date type="datePub">2002</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="fr">Informatique musicale</term>
                <term xml:lang="fr">NA</term>
              </keywords>
              <classCode scheme="halDomain" n="spi.acou">Engineering Sciences [physics]/Acoustics [physics.class-ph]</classCode>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</classCode>
              <classCode scheme="halDomain" n="scco.neur">Cognitive science/Neuroscience</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>This paper deals with the automatic generation of music audio summaries from signal analysis without the use of any other information. The strategy employed here is to consider the audio signal as a succession of “states” (at various scales) corresponding to the structure (at various scales) of a piece of music. This is, of course, only applicable to certain kinds of musical genres based on some kind of repetition. From the audio signal, we first derive dynamic features representing the time evolution of the energy content in various frequency bands. These features constitute our observations from which we derive a representation of the music in terms of “states”. Since human segmentation and grouping performs better upon subsequent hearings, this “natural” approach is followed here. The first pass of the proposed algorithm uses segmentation in order to create “templates”. The second pass uses these templates in order to propose a structure of the music using unsupervised learning methods (Kmeans and hidden Markov model). The audio summary is finally constructed by choosing a representative example of each state. Further refinements of the summary audio signal construction, uses overlapadd, and a tempo detection/ beat alignment in order to improve the audio quality of the created summary.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-410616" status="OLD">
          <orgName>Analyse et synthèse sonores [Paris]</orgName>
          <desc>
            <address>
              <addrLine>1, place Igor stravinsky, 75004, Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://anasynth.ircam.fr/home/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1374" type="direct"/>
            <relation active="#struct-5234" type="indirect"/>
            <relation active="#struct-93591" type="indirect"/>
            <relation name="UMR9912" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1374" status="OLD">
          <idno type="RNSR">198319352N</idno>
          <orgName>Sciences et Technologies de la Musique et du Son</orgName>
          <orgName type="acronym">STMS</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>1 Place Igor Stravinsky 75004 PARIS</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ircam.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5234" type="direct"/>
            <relation active="#struct-93591" type="direct"/>
            <relation name="UMR9912" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-5234" status="VALID">
          <idno type="ROR">https://ror.org/0121jnt59</idno>
          <orgName>Institut de Recherche et Coordination Acoustique/Musique</orgName>
          <orgName type="acronym">IRCAM</orgName>
          <desc>
            <address>
              <addrLine>1, place Igor Stravinsky 75004 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ircam.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.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>
    </back>
  </text>
</TEI>