<?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-05244860</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="2026-05-19T15:26:33+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Physically Informed Spatial Regularization for Sound Event Localization and Detection</title>
            <author role="aut">
              <persName>
                <forename type="first">Haocheng</forename>
                <surname>Liu</surname>
              </persName>
              <email type="md5">a1e053d60b6c0e1257a46c64d3eaa66a</email>
              <email type="domain">ip-paris.fr</email>
              <idno type="idhal" notation="string">haocheng-liu</idno>
              <idno type="idhal" notation="numeric">1579846</idno>
              <idno type="halauthorid" notation="string">3031189-1579846</idno>
              <affiliation ref="#struct-554452"/>
              <affiliation ref="#struct-554512"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Diego</forename>
                <surname>Di Carlo</surname>
              </persName>
              <idno type="halauthorid">1165672-0</idno>
              <affiliation ref="#struct-569958"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aditya</forename>
                <forename type="middle">Arie</forename>
                <surname>Nugraha</surname>
              </persName>
              <email type="md5">baec7ba689fcda4261289b932762b5ca</email>
              <email type="domain">riken.jp</email>
              <idno type="idhal" notation="string">aanugraha</idno>
              <idno type="idhal" notation="numeric">4303</idno>
              <idno type="halauthorid" notation="string">2552364-4303</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5424-747X</idno>
              <idno type="IDREF">https://www.idref.fr/223438278</idno>
              <affiliation ref="#struct-569958"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kazuyoshi</forename>
                <surname>Yoshii</surname>
              </persName>
              <idno type="halauthorid">1216004-0</idno>
              <affiliation ref="#struct-237161"/>
              <affiliation ref="#struct-569958"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gaël</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">51091-14146</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"/>
              <affiliation ref="#struct-554512"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mathieu</forename>
                <surname>Fontaine</surname>
              </persName>
              <email type="md5">89a2d201f3abde448209bbdfb6c03b44</email>
              <email type="domain">telecom-paris.fr</email>
              <idno type="idhal" notation="string">mathieu-fontaine</idno>
              <idno type="idhal" notation="numeric">13405</idno>
              <idno type="halauthorid" notation="string">34886-13405</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7657-6271</idno>
              <idno type="IDREF">https://www.idref.fr/236886681</idno>
              <affiliation ref="#struct-554452"/>
              <affiliation ref="#struct-554512"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Haocheng</forename>
                <surname>LIU</surname>
              </persName>
              <email type="md5">227dd2384bcd136d767a6c52208989ae</email>
              <email type="domain">telecom-paris.fr</email>
            </editor>
            <funder ref="#projanr-66316"/>
            <funder ref="#projanr-185718"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-09-08 13:27:18</date>
              <date type="whenModified">2026-02-07 05:32:08</date>
              <date type="whenReleased">2025-09-12 08:51:23</date>
              <date type="whenProduced">2025-10-12</date>
              <date type="whenEndEmbargoed">2025-09-08</date>
              <ref type="file" target="https://hal.science/hal-05244860v1/document">
                <date notBefore="2025-09-08"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05244860v1/file/2025_WASPAA_Physically_Informed_Spatial_Regularization_for_SELD.pdf" id="file-5244860-4510563">
                <date notBefore="2025-09-08"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1343576">
                <persName>
                  <forename>Haocheng</forename>
                  <surname>LIU</surname>
                </persName>
                <email type="md5">227dd2384bcd136d767a6c52208989ae</email>
                <email type="domain">telecom-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05244860</idno>
            <idno type="halUri">https://hal.science/hal-05244860</idno>
            <idno type="halBibtex">liu:hal-05244860</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Workshop on Applications of Signal Processing to Audio and Acoustics&lt;/i&gt;, Oct 2025, Tahoe City, California, United States</idno>
            <idno type="halRef">IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2025, Tahoe City, California, United States</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5244860-4510563"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="GENCI">Publications ayant eu recours aux supercalculateurs du GENCI</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="ANR">ANR</idno>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</idno>
            <idno type="stamp" n="ANR-IA-22" corresp="ANR-IA">ANR-IA-22</idno>
            <idno type="stamp" n="ANR-IA-23" corresp="ANR-IA">ANR-IA-23</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Physically Informed Spatial Regularization for Sound Event Localization and Detection</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Haocheng</forename>
                    <surname>Liu</surname>
                  </persName>
                  <email type="md5">a1e053d60b6c0e1257a46c64d3eaa66a</email>
                  <email type="domain">ip-paris.fr</email>
                  <idno type="idhal" notation="string">haocheng-liu</idno>
                  <idno type="idhal" notation="numeric">1579846</idno>
                  <idno type="halauthorid" notation="string">3031189-1579846</idno>
                  <affiliation ref="#struct-554452"/>
                  <affiliation ref="#struct-554512"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Diego</forename>
                    <surname>Di Carlo</surname>
                  </persName>
                  <idno type="halauthorid">1165672-0</idno>
                  <affiliation ref="#struct-569958"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aditya</forename>
                    <forename type="middle">Arie</forename>
                    <surname>Nugraha</surname>
                  </persName>
                  <email type="md5">baec7ba689fcda4261289b932762b5ca</email>
                  <email type="domain">riken.jp</email>
                  <idno type="idhal" notation="string">aanugraha</idno>
                  <idno type="idhal" notation="numeric">4303</idno>
                  <idno type="halauthorid" notation="string">2552364-4303</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5424-747X</idno>
                  <idno type="IDREF">https://www.idref.fr/223438278</idno>
                  <affiliation ref="#struct-569958"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kazuyoshi</forename>
                    <surname>Yoshii</surname>
                  </persName>
                  <idno type="halauthorid">1216004-0</idno>
                  <affiliation ref="#struct-237161"/>
                  <affiliation ref="#struct-569958"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gaël</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">51091-14146</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"/>
                  <affiliation ref="#struct-554512"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mathieu</forename>
                    <surname>Fontaine</surname>
                  </persName>
                  <email type="md5">89a2d201f3abde448209bbdfb6c03b44</email>
                  <email type="domain">telecom-paris.fr</email>
                  <idno type="idhal" notation="string">mathieu-fontaine</idno>
                  <idno type="idhal" notation="numeric">13405</idno>
                  <idno type="halauthorid" notation="string">34886-13405</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7657-6271</idno>
                  <idno type="IDREF">https://www.idref.fr/236886681</idno>
                  <affiliation ref="#struct-554452"/>
                  <affiliation ref="#struct-554512"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>IEEE Workshop on Applications of Signal Processing to Audio and Acoustics</title>
                  <date type="start">2025-10-12</date>
                  <date type="end">2025-10-15</date>
                  <settlement>Tahoe City, California</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint/>
              </monogr>
            </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="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>Building Sound Event Localization and Detection (SELD) models that are robust to diverse acoustic environments remains one of the major challenges in multichannel signal processing, as reflections and reverberation can significantly confuse both the source direction and event detection. Introducing priors such as microphone geometry or room impulse response (RIR) into the model has proven effective in addressing this issue. Existing methods typically incorporate such priors in a deterministic way, often through data augmentation to enlarge data diversity. However, the uncertainty arising from the complex nature of audio acoustics remains largely underexplored in the SELD literature and naturally call for incorporating a stochastic modeling of acoustic prior. In this paper, we propose regularizing deep learning based SELD models with a physically constructed spatial covariance matrix (SCM) based on the estimated direction of arrival (DOA) and sound event detection (SED).</p>
            </abstract>
            <particDesc>
              <org type="ir" xml:id="fr-esr-fdr-ir-064">
                <orgName type="acronym">GENCI</orgName>
                <idno type="wikidata">Q3093180</idno>
              </org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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="department" xml:id="struct-554512" status="VALID">
          <orgName>Département Images, Données, Signal</orgName>
          <orgName type="acronym">IDS</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019)</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr/fr/recherche/laboratoires/laboratoire-traitement-et-communication-de-linformation-ltci/les-departements-denseignement-et-recherche</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300362" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-569958" status="VALID">
          <idno type="ROR">https://ror.org/03ckxwf91</idno>
          <orgName>RIKEN Center for Advanced Intelligence Project [Tokyo]</orgName>
          <orgName type="acronym">RIKEN AIP</orgName>
          <desc>
            <address>
              <addrLine>Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">https://www.riken.jp/en/research/labs/aip/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-26075" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-237161" status="VALID">
          <idno type="IdRef">033102953</idno>
          <idno type="ISNI">0000 0004 0372 2033</idno>
          <idno type="ROR">https://ror.org/02kpeqv85</idno>
          <idno type="Wikidata">Q336264</idno>
          <orgName>Kyōto daigaku = Kyoto University</orgName>
          <date type="start">1897-01-01</date>
          <desc>
            <address>
              <addrLine>Yoshidahonmachi, Sakyo Ward, Kyoto, Kyoto Prefecture 606-8501</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">http://www.kyoto-u.ac.jp/en</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="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-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>
        <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-26075" status="VALID">
          <idno type="ISNI">0000 0000 9446 5255</idno>
          <idno type="ROR">https://ror.org/01sjwvz98</idno>
          <idno type="Wikidata">Q1153275</idno>
          <orgName>RIKEN - Institute of Physical and Chemical Research [Japon]</orgName>
          <orgName type="acronym">RIKEN</orgName>
          <date type="start">1917-03-20</date>
          <desc>
            <address>
              <addrLine>Hirosawa 2-1, Wako, Saitama 351-0198</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">https://www.riken.jp/en/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-66316" status="VALID">
          <idno type="anr">ANR-22-CE23-0011</idno>
          <orgName>SAROUMANE</orgName>
          <desc>Segmentation et regroupement de locuteurs via un modèle robuste unifié audio spatial et multimodal</desc>
          <date type="start">2022</date>
        </org>
        <org type="anrProject" xml:id="projanr-185718" status="VALID">
          <idno type="anr">ANR-23-IACL-0005</idno>
          <orgName>Hi! PARIS Cluster 2030</orgName>
          <desc>Hi! PARIS AI cluster 2030 for Science, Business and Society</desc>
          <date type="start">2023</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>