<?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-03566663</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="2026-05-24T00:46:16+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Audio Defect Detection in Music with Deep Networks</title>
            <author role="aut">
              <persName>
                <forename type="first">Daniel</forename>
                <surname>Wolff</surname>
              </persName>
              <email type="md5">b008e1e1c36a265d41efff59f0832cac</email>
              <email type="domain">posteo.de</email>
              <idno type="idhal" notation="numeric">1125242</idno>
              <idno type="halauthorid" notation="string">2105679-1125242</idno>
              <affiliation ref="#struct-541780"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rémi</forename>
                <surname>Mignot</surname>
              </persName>
              <email type="md5">ed2c52ff3c97c5834fbe61e71f99379f</email>
              <email type="domain">ircam.fr</email>
              <idno type="idhal" notation="numeric">884002</idno>
              <idno type="halauthorid" notation="string">442801-884002</idno>
              <affiliation ref="#struct-541780"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Axel</forename>
                <surname>Roebel</surname>
              </persName>
              <email type="md5">f5827691d18202684001d3300c088d9c</email>
              <email type="domain">ircam.fr</email>
              <idno type="idhal" notation="string">axel-roebel</idno>
              <idno type="idhal" notation="numeric">4527</idno>
              <idno type="halauthorid" notation="string">20620-4527</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6136-4391</idno>
              <idno type="IDREF">https://www.idref.fr/227186079</idno>
              <idno type="IDREF">https://www.idref.fr/163747032</idno>
              <affiliation ref="#struct-541780"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Daniel</forename>
                <surname>Wolff</surname>
              </persName>
              <email type="md5">b008e1e1c36a265d41efff59f0832cac</email>
              <email type="domain">posteo.de</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-02-11 16:35:34</date>
              <date type="whenModified">2024-10-30 13:28:40</date>
              <date type="whenReleased">2022-02-23 12:49:54</date>
              <date type="whenProduced">2021-11-07</date>
              <date type="whenEndEmbargoed">2022-02-11</date>
              <ref type="file" target="https://hal.science/hal-03566663v1/document">
                <date notBefore="2022-02-11"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03566663v1/file/000095_paper.pdf" id="file-3566663-3123403">
                <date notBefore="2022-02-11"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1135618">
                <persName>
                  <forename>Daniel</forename>
                  <surname>Wolff</surname>
                </persName>
                <email type="md5">b008e1e1c36a265d41efff59f0832cac</email>
                <email type="domain">posteo.de</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03566663</idno>
            <idno type="halUri">https://hal.science/hal-03566663</idno>
            <idno type="halBibtex">wolff:hal-03566663</idno>
            <idno type="halRefHtml">&lt;i&gt;22nd Int. Society for Music Information Retrieval Conference (ISMIR 2021)&lt;/i&gt;, Nov 2021, Online, France</idno>
            <idno type="halRef">22nd Int. Society for Music Information Retrieval Conference (ISMIR 2021), Nov 2021, Online, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3566663-3123403"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="GENCI">Publications ayant eu recours aux supercalculateurs du GENCI</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</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>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Audio Defect Detection in Music with Deep Networks</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Daniel</forename>
                    <surname>Wolff</surname>
                  </persName>
                  <email type="md5">b008e1e1c36a265d41efff59f0832cac</email>
                  <email type="domain">posteo.de</email>
                  <idno type="idhal" notation="numeric">1125242</idno>
                  <idno type="halauthorid" notation="string">2105679-1125242</idno>
                  <affiliation ref="#struct-541780"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rémi</forename>
                    <surname>Mignot</surname>
                  </persName>
                  <email type="md5">ed2c52ff3c97c5834fbe61e71f99379f</email>
                  <email type="domain">ircam.fr</email>
                  <idno type="idhal" notation="numeric">884002</idno>
                  <idno type="halauthorid" notation="string">442801-884002</idno>
                  <affiliation ref="#struct-541780"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Axel</forename>
                    <surname>Roebel</surname>
                  </persName>
                  <email type="md5">f5827691d18202684001d3300c088d9c</email>
                  <email type="domain">ircam.fr</email>
                  <idno type="idhal" notation="string">axel-roebel</idno>
                  <idno type="idhal" notation="numeric">4527</idno>
                  <idno type="halauthorid" notation="string">20620-4527</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6136-4391</idno>
                  <idno type="IDREF">https://www.idref.fr/227186079</idno>
                  <idno type="IDREF">https://www.idref.fr/163747032</idno>
                  <affiliation ref="#struct-541780"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>22nd Int. Society for Music Information Retrieval Conference (ISMIR 2021)</title>
                  <date type="start">2021-11-07</date>
                  <settlement>Online</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-mm">Computer Science [cs]/Multimedia [cs.MM]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</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>With increasing amounts of music being digitally transferred from production to distribution, automatic means of determining media quality are needed. Protection mechanisms in digital audio processing tools have not eliminated the need of production entities located downstream the distribution chain to assess audio quality and detect defects inserted further upstream. Such analysis often relies on the received audio and scarce meta-data alone. Deliberate use of artefacts such as clicks in popular music as well as more recent defects stemming from corruption in modern audio encodings call for data-centric and contextsensitive solutions for detection. We present a convolutional network architecture following end-to-end encoderdecoder configuration to develop detectors for two exemplary audio defects. A click detector is trained and compared to a traditional signal processing method, with a discussion on context sensitivity. Additional post-processing is used for data augmentation and workflow simulation. The ability of our models to capture variance is explored in a detector for artefacts from decompression of corrupted MP3 compressed audio. For both tasks we describe the synthetic generation of artefacts for controlled detector training and evaluation. We evaluate our detectors on the large open-source Free Music Archive (FMA) and genrespecific datasets.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-541780" status="VALID">
          <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-541779" type="direct"/>
            <relation active="#struct-5234" type="indirect"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR9912" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-541779" status="VALID">
          <idno type="IdRef">24096277X</idno>
          <idno type="RNSR">198319352N</idno>
          <idno type="ROR">025xvn046</idno>
          <orgName>Sciences et Technologies de la Musique et du Son</orgName>
          <orgName type="acronym">STMS</orgName>
          <date type="start">2018-01-01</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-413221" 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="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.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>