<?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-02005102v2</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="2026-05-17T20:03:33+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization</title>
            <author role="aut">
              <persName>
                <forename type="first">Simon</forename>
                <surname>Leglaive</surname>
              </persName>
              <email type="md5">0efe3e1da4e078364572ef1e1f95d8f6</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">simon-leglaive</idno>
              <idno type="idhal" notation="numeric">20853</idno>
              <idno type="halauthorid" notation="string">27069-20853</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8219-1298</idno>
              <idno type="IDREF">https://www.idref.fr/25312171X</idno>
              <affiliation ref="#struct-1042500"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Girin</surname>
              </persName>
              <email type="md5">6822181ca0d278df7c3873c6c99ad700</email>
              <email type="domain">gipsa-lab.grenoble-inp.fr</email>
              <idno type="idhal" notation="string">laurent-girin</idno>
              <idno type="idhal" notation="numeric">3682</idno>
              <idno type="halauthorid" notation="string">11768-3682</idno>
              <idno type="IDREF">https://www.idref.fr/088998037</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9214-8760</idno>
              <idno type="VIAF">https://viaf.org/viaf/193925361</idno>
              <idno type="ISNI">http://isni.org/isni/0000000356924379</idno>
              <orgName ref="#struct-89889"/>
              <affiliation ref="#struct-1042673"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Radu</forename>
                <surname>Horaud</surname>
              </persName>
              <email type="md5">dac696566b611a791aba8a50c3a735c5</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">radu-horaud</idno>
              <idno type="idhal" notation="numeric">16183</idno>
              <idno type="halauthorid" notation="string">21785-16183</idno>
              <idno type="ARXIV">https://arxiv.org/a/horaud_r_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5232-024X</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=Lvit5RIAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/032302495</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-1042500"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Simon</forename>
                <surname>Leglaive</surname>
              </persName>
              <email type="md5">0efe3e1da4e078364572ef1e1f95d8f6</email>
              <email type="domain">centralesupelec.fr</email>
            </editor>
            <funder ref="#projeurop-98080"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2019-02-08 11:20:54</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2019-04-30 15:48:09</date>
              <date type="whenModified">2025-09-27 18:44:39</date>
              <date type="whenReleased">2019-05-02 09:36:38</date>
              <date type="whenProduced">2019-05-12</date>
              <date type="whenEndEmbargoed">2019-04-30</date>
              <ref type="file" target="https://inria.hal.science/hal-02005102v2/document">
                <date notBefore="2019-04-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-02005102v2/file/LGH-icassp2019.pdf" id="file-2115950-2111613">
                <date notBefore="2019-04-30"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1811.06713"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="449950">
                <persName>
                  <forename>Simon</forename>
                  <surname>Leglaive</surname>
                </persName>
                <email type="md5">0efe3e1da4e078364572ef1e1f95d8f6</email>
                <email type="domain">centralesupelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02005102</idno>
            <idno type="halUri">https://inria.hal.science/hal-02005102</idno>
            <idno type="halBibtex">leglaive:hal-02005102</idno>
            <idno type="halRefHtml">&lt;i&gt;ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing&lt;/i&gt;, May 2019, Brighton, United Kingdom. pp.101-105, &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICASSP.2019.8683704"&gt;&amp;#x27E8;10.1109/ICASSP.2019.8683704&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. pp.101-105, &amp;#x27E8;10.1109/ICASSP.2019.8683704&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2115950-2111613"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="INRIA-RHA">INRIA Grenoble - Rhône-Alpes</idno>
            <idno type="stamp" n="GIPSA">Grenoble Images Parole Signal Automatique</idno>
            <idno type="stamp" n="GIPSA-DPC" corresp="GIPSA">Département Parole et Cognition</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LJK">Laboratoire Jean Kuntzmann</idno>
            <idno type="stamp" n="LJK_GI" corresp="LJK">Département Géométrie et Images</idno>
            <idno type="stamp" n="LJK_GI_PERCEPTION" corresp="LJK_GI">PERCEPTION</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="GIPSA-CRISSP">CRISSP</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="UGA-COMUE">Université Grenoble Alpes [2016-2019]</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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">Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Simon</forename>
                    <surname>Leglaive</surname>
                  </persName>
                  <email type="md5">0efe3e1da4e078364572ef1e1f95d8f6</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">simon-leglaive</idno>
                  <idno type="idhal" notation="numeric">20853</idno>
                  <idno type="halauthorid" notation="string">27069-20853</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8219-1298</idno>
                  <idno type="IDREF">https://www.idref.fr/25312171X</idno>
                  <affiliation ref="#struct-1042500"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Girin</surname>
                  </persName>
                  <email type="md5">6822181ca0d278df7c3873c6c99ad700</email>
                  <email type="domain">gipsa-lab.grenoble-inp.fr</email>
                  <idno type="idhal" notation="string">laurent-girin</idno>
                  <idno type="idhal" notation="numeric">3682</idno>
                  <idno type="halauthorid" notation="string">11768-3682</idno>
                  <idno type="IDREF">https://www.idref.fr/088998037</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9214-8760</idno>
                  <idno type="VIAF">https://viaf.org/viaf/193925361</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000356924379</idno>
                  <orgName ref="#struct-89889"/>
                  <affiliation ref="#struct-1042673"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Radu</forename>
                    <surname>Horaud</surname>
                  </persName>
                  <email type="md5">dac696566b611a791aba8a50c3a735c5</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">radu-horaud</idno>
                  <idno type="idhal" notation="numeric">16183</idno>
                  <idno type="halauthorid" notation="string">21785-16183</idno>
                  <idno type="ARXIV">https://arxiv.org/a/horaud_r_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5232-024X</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=Lvit5RIAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/032302495</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-1042500"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing</title>
                  <date type="start">2019-05-12</date>
                  <date type="end">2019-05-17</date>
                  <settlement>Brighton</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">101-105</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICASSP.2019.8683704</idno>
              <ref type="publisher">https://2019.ieeeicassp.org</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">local Gaussian modeling</term>
                <term xml:lang="en">non-negative matrix factorization</term>
                <term xml:lang="en">variational autoencoders</term>
                <term xml:lang="en">Monte Carlo expectation-maximization</term>
                <term xml:lang="en">Multichannel speech enhancement</term>
              </keywords>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</classCode>
              <classCode scheme="halDomain" n="info.info-ne">Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]</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>In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian modeling framework. We propose to use a neural network for modeling the speech spectro-temporal content. The parameters of this supervised model are learned using the framework of variational autoencoders. The noisy recording environment is supposed to be unknown, so the noise spectro-temporal modeling remains unsupervised and is based on non-negative matrix factorization (NMF). We develop a Monte Carlo expectation-maximization algorithm and we experimentally show that the proposed approach outperforms its NMF-based counterpart, where speech is modeled using supervised NMF.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1042500" status="OLD">
          <idno type="RNSR">200818261U</idno>
          <orgName>Interpretation and Modelling of Images and Videos</orgName>
          <orgName type="acronym">PERCEPTION</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>INRIA Rhône-Alpes 655 avenue de l'Europe 38330 Montbonnot, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/perception</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2497" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-89889" type="direct"/>
            <relation active="#struct-1042161" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1042673" status="OLD">
          <orgName>GIPSA - Cognitive Robotics, Interactive Systems, &amp; Speech Processing</orgName>
          <orgName type="acronym">GIPSA-CRISSP</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.gipsa-lab.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042667" type="direct"/>
            <relation active="#struct-1042376" type="indirect"/>
            <relation active="#struct-89889" type="indirect"/>
            <relation active="#struct-300275" type="indirect"/>
            <relation name="UMR5216" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2497" status="VALID">
          <idno type="RNSR">199218244V</idno>
          <idno type="ROR">https://ror.org/00n8d6z93</idno>
          <orgName>Centre Inria de l'Université Grenoble Alpes</orgName>
          <desc>
            <address>
              <addrLine>Inovallée655 avenue de l'Europe38330 Montbonnot</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/grenoble</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </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="institution" xml:id="struct-89889" status="OLD">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2007-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1042161" status="OLD">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">000000040383676X</idno>
          <idno type="RNSR">200711891Z</idno>
          <idno type="ROR">https://ror.org/04ett5b41</idno>
          <orgName>Laboratoire Jean Kuntzmann</orgName>
          <orgName type="acronym">LJK</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment IMAG, CS 40700, F-38058 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ljk.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-89889" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
            <relation active="#struct-445543" type="direct"/>
          </listRelation>
        </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-445543" status="OLD">
          <idno type="IdRef">188399275</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes [2016-2019]</orgName>
          <orgName type="acronym">UGA [2016-2019]</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="department" xml:id="struct-1042667" status="OLD">
          <orgName>Département Parole et Cognition</orgName>
          <orgName type="acronym">GIPSA-DPC</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>11 rue des Mathématiques, Grenoble Campus BP46, 38402 SAINT MARTIN D'HERES</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.gipsa-lab.fr/recherche/departement-parole-cognition.php</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042376" type="direct"/>
            <relation active="#struct-89889" type="indirect"/>
            <relation active="#struct-300275" type="indirect"/>
            <relation name="UMR5216" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1042376" status="OLD">
          <idno type="IdRef">137251122</idno>
          <idno type="ISNI">0000000118823396 </idno>
          <idno type="RNSR">200711885T</idno>
          <idno type="ROR">https://ror.org/02wrme198</idno>
          <orgName>Grenoble Images Parole Signal Automatique</orgName>
          <orgName type="acronym">GIPSA-lab</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab 11 rue des Mathématiques, Grenoble Campus BP46F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.gipsa-lab.inpg.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-89889" type="direct"/>
            <relation active="#struct-300275" type="direct"/>
            <relation name="UMR5216" active="#struct-441569" type="direct"/>
            <relation active="#struct-445543" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300275" status="OLD">
          <idno type="IdRef">026388804</idno>
          <orgName>Institut National Polytechnique de Grenoble</orgName>
          <orgName type="acronym">INPG</orgName>
          <date type="end">2006-12-31</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="europeanProject" xml:id="projeurop-98080" status="VALID">
          <idno type="number">340113</idno>
          <idno type="program">ERC-2013-ADG</idno>
          <idno type="call">ERC-2013-ADG</idno>
          <orgName>VHIA</orgName>
          <desc>Vision and Hearing in Action</desc>
          <date type="start">2014-01-02</date>
          <date type="end">2019-01-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>