<?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-04029145</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="2026-05-20T01:26:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Explainable Audio Classification of Playing Techniques with Layer-wise Relevance Propagation</title>
            <author role="aut">
              <persName>
                <forename type="first">Changhong</forename>
                <surname>Wang</surname>
              </persName>
              <email type="md5">1dd616cc8683c809c432e8bf438e38e3</email>
              <email type="domain">telecom-paris.fr</email>
              <idno type="idhal" notation="string">changhong-wang</idno>
              <idno type="idhal" notation="numeric">1237245</idno>
              <idno type="halauthorid" notation="string">2242394-1237245</idno>
              <affiliation ref="#struct-484335"/>
              <affiliation ref="#struct-1048346"/>
              <affiliation ref="#struct-1152416"/>
            </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">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-1088564"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Changhong</forename>
                <surname>Wang</surname>
              </persName>
              <email type="md5">1dd616cc8683c809c432e8bf438e38e3</email>
              <email type="domain">telecom-paris.fr</email>
            </editor>
            <funder>Supported by an Atlanstic2020 project on Trainable Acoustic Sensors (TrAcS)</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-03-14 17:57:48</date>
              <date type="whenModified">2026-02-03 03:32:02</date>
              <date type="whenReleased">2023-03-14 18:35:28</date>
              <date type="whenProduced">2023-06-04</date>
              <date type="whenEndEmbargoed">2023-03-14</date>
              <ref type="file" target="https://hal.science/hal-04029145v1/document">
                <date notBefore="2023-03-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04029145v1/file/wang_ICASSP23_final.pdf" id="file-4029145-3508462">
                <date notBefore="2023-03-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1397274">
                <persName>
                  <forename>Changhong</forename>
                  <surname>Wang</surname>
                </persName>
                <email type="md5">1dd616cc8683c809c432e8bf438e38e3</email>
                <email type="domain">telecom-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04029145</idno>
            <idno type="halUri">https://hal.science/hal-04029145</idno>
            <idno type="halBibtex">wang:hal-04029145</idno>
            <idno type="halRefHtml">&lt;i&gt;2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)&lt;/i&gt;, Jun 2023, Rhodes, Greece. pp.1-5, &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICASSP49357.2023.10095894"&gt;&amp;#x27E8;10.1109/ICASSP49357.2023.10095894&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Jun 2023, Rhodes, Greece. pp.1-5, &amp;#x27E8;10.1109/ICASSP49357.2023.10095894&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4029145-3508462"/></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="ENST">Ecole Nationale Supérieure des Télécommunications</idno>
            <idno type="stamp" n="TELECOM-PARISTECH" corresp="PARISTECH">Télécom Paris</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="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="IP_PARIS">Institut Polytechnique de Paris</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>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</idno>
            <idno type="stamp" n="IP-PARIS-DEPARTEMENT-MATHEMATIQUES">Département de Mathèmatiques</idno>
            <idno type="stamp" n="IP-PARIS-MATHEMATIQUES">IP Paris Département de Mathématiques</idno>
            <idno type="stamp" n="IP-PARIS-INFORMATION-COMMUNICATION-ELECTRONIQUE">IP Paris Département d'Information, de Communication et d'Électronique</idno>
            <idno type="stamp" n="IP-PARIS-INFORMATIQUE-DONNEES-ET-IA">IP Paris Département d'Informatique, de Données et d'IA</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">Explainable Audio Classification of Playing Techniques with Layer-wise Relevance Propagation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Changhong</forename>
                    <surname>Wang</surname>
                  </persName>
                  <email type="md5">1dd616cc8683c809c432e8bf438e38e3</email>
                  <email type="domain">telecom-paris.fr</email>
                  <idno type="idhal" notation="string">changhong-wang</idno>
                  <idno type="idhal" notation="numeric">1237245</idno>
                  <idno type="halauthorid" notation="string">2242394-1237245</idno>
                  <affiliation ref="#struct-484335"/>
                  <affiliation ref="#struct-1048346"/>
                  <affiliation ref="#struct-1152416"/>
                </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">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-1088564"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)</title>
                  <date type="start">2023-06-04</date>
                  <date type="end">2023-06-10</date>
                  <settlement>Rhodes</settlement>
                  <country key="GR">Greece</country>
                </meeting>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">1-5</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICASSP49357.2023.10095894</idno>
              <ref type="publisher">https://2023.ieeeicassp.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Layer-wise relevance propagation</term>
                <term xml:lang="en">scattering transform</term>
                <term xml:lang="en">playing technique recognition</term>
                <term xml:lang="en">music signal analysis</term>
              </keywords>
              <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-ts">Computer Science [cs]/Signal and Image Processing</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>
              <classCode scheme="https://namespace.ccsd.cnrs.fr/hal/metadata/afssa_thematique" n="1">Affaires internationales</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Deep convolutional networks (convnets) in the time-frequency domain can learn an accurate and fine-grained categorization of sounds. For example, in the context of music signal analysis, this categorization may correspond to a taxonomy of playing techniques: vibrato, tremolo, trill, and so forth. However, convnets lack an explicit connection with the neurophysiological underpinnings of musical timbre perception. In this article, we propose a data-driven approach to explain audio classification in terms of physical attributes in sound production. We borrow from current literature in "explainable AI" (XAI) to study the predictions of a convnet which achieves an almost perfect score on a challenging task: i.e., the classification of five comparable real-world playing techniques from 30 instruments spanning seven octaves. Mapping the signal into the carrier-modulation domain using scattering transform, we decompose the networks' predictions over this domain with layer-wise relevance propagation. We find that regions highly-relevant to the predictions localized around the physical attributes with which the playing techniques are performed.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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="institution" xml:id="struct-1152416" status="INCOMING">
          <orgName>Telecom-Paris, Institut Polytechnique de Paris</orgName>
          <orgName type="acronym">LTCI</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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="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-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>
        <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="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>