<?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-02355613v2</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="2026-05-05T04:14:20+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">SLOGD: Speaker Location Guided Deflation Approach to Speech Separation</title>
            <author role="aut">
              <persName>
                <forename type="first">Sunit</forename>
                <surname>Sivasankaran</surname>
              </persName>
              <email type="md5">2630c85b983e220864602406360cc912</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">sunit-sivasankaran</idno>
              <idno type="idhal" notation="numeric">12596</idno>
              <idno type="halauthorid" notation="string">27009-12596</idno>
              <idno type="IDREF">https://www.idref.fr/249104563</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9285-0234</idno>
              <affiliation ref="#struct-420403"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Emmanuel</forename>
                <surname>Vincent</surname>
              </persName>
              <email type="md5">06c8a35e507be1d816f58461ca2239ea</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">emmanuelv</idno>
              <idno type="idhal" notation="numeric">1256</idno>
              <idno type="halauthorid" notation="string">4290-1256</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0183-7289</idno>
              <idno type="IDREF">https://www.idref.fr/089360176</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-420403"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Dominique</forename>
                <surname>Fohr</surname>
              </persName>
              <email type="md5">8e5e638ec2a51d07ccd00424312223ce</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">dominique-fohr</idno>
              <idno type="idhal" notation="numeric">15652</idno>
              <idno type="halauthorid" notation="string">3052-15652</idno>
              <idno type="IDREF">https://www.idref.fr/031092942</idno>
              <orgName ref="#struct-441569"/>
              <affiliation ref="#struct-420403"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sunit</forename>
                <surname>Sivasankaran</surname>
              </persName>
              <email type="md5">a0e1298116b614dc65d9339df2ef0913</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projanr-44647"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2019-11-08 12:58:04</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2020-02-14 09:49:30</date>
              <date type="whenModified">2025-11-04 11:59:11</date>
              <date type="whenReleased">2020-02-14 13:03:26</date>
              <date type="whenProduced">2020-05-04</date>
              <date type="whenEndEmbargoed">2020-02-14</date>
              <ref type="file" target="https://inria.hal.science/hal-02355613v2/document">
                <date notBefore="2020-02-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-02355613v2/file/sivasankaran.pdf" id="file-2478705-2356099">
                <date notBefore="2020-02-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="321998">
                <persName>
                  <forename>Sunit</forename>
                  <surname>Sivasankaran</surname>
                </persName>
                <email type="md5">a0e1298116b614dc65d9339df2ef0913</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02355613</idno>
            <idno type="halUri">https://inria.hal.science/hal-02355613</idno>
            <idno type="halBibtex">sivasankaran:hal-02355613</idno>
            <idno type="halRefHtml">&lt;i&gt;ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing&lt;/i&gt;, May 2020, Barcelona, Spain</idno>
            <idno type="halRef">ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2478705-2356099"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
            <idno type="stamp" n="GRID5000">Grid'5000</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="SLICES-FR">Publications from users of the SILECS research infrastructure</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</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">SLOGD: Speaker Location Guided Deflation Approach to Speech Separation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Sunit</forename>
                    <surname>Sivasankaran</surname>
                  </persName>
                  <email type="md5">2630c85b983e220864602406360cc912</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">sunit-sivasankaran</idno>
                  <idno type="idhal" notation="numeric">12596</idno>
                  <idno type="halauthorid" notation="string">27009-12596</idno>
                  <idno type="IDREF">https://www.idref.fr/249104563</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9285-0234</idno>
                  <affiliation ref="#struct-420403"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Emmanuel</forename>
                    <surname>Vincent</surname>
                  </persName>
                  <email type="md5">06c8a35e507be1d816f58461ca2239ea</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">emmanuelv</idno>
                  <idno type="idhal" notation="numeric">1256</idno>
                  <idno type="halauthorid" notation="string">4290-1256</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0183-7289</idno>
                  <idno type="IDREF">https://www.idref.fr/089360176</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-420403"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Dominique</forename>
                    <surname>Fohr</surname>
                  </persName>
                  <email type="md5">8e5e638ec2a51d07ccd00424312223ce</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">dominique-fohr</idno>
                  <idno type="idhal" notation="numeric">15652</idno>
                  <idno type="halauthorid" notation="string">3052-15652</idno>
                  <idno type="IDREF">https://www.idref.fr/031092942</idno>
                  <orgName ref="#struct-441569"/>
                  <affiliation ref="#struct-420403"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing</title>
                  <date type="start">2020-05-04</date>
                  <date type="end">2020-05-08</date>
                  <settlement>Barcelona</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Index Terms-Speech separation</term>
                <term xml:lang="en">localization</term>
                <term xml:lang="en">deflation</term>
                <term xml:lang="en">Speech separation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <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="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>Speech separation is the process of separating multiple speakers from an audio recording. In this work we propose to separate the sources using a Speaker LOcalization Guided Deflation (SLOGD) approach wherein we estimate the sources iteratively. In each iteration we first estimate the location of the speaker and use it to estimate a mask corresponding to the localized speaker. The estimated source is removed from the mixture before estimating the location and mask of the next source. Experiments are conducted on a reverberated, noisy multichannel version of the well-studied WSJ-2MIX dataset using word error rate (WER) as a metric. The proposed method achieves a WER of 44.2 %, a 34% relative improvement over the system without separation and 17% relative improvement over Conv-TasNet.</p>
            </abstract>
            <particDesc>
              <org type="consortium">Grid'5000</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-420403" status="VALID">
          <idno type="RNSR">201421147E</idno>
          <idno type="ROR">https://ror.org/02mv3qy73</idno>
          <orgName>Speech Modeling for Facilitating Oral-Based Communication</orgName>
          <orgName type="acronym">MULTISPEECH</orgName>
          <date type="start">2015-07-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/multispeech</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-129671" status="VALID">
          <idno type="RNSR">198618246Y</idno>
          <idno type="ROR">https://ror.org/03fcjvn64</idno>
          <orgName>Centre Inria de l'Université de Lorraine</orgName>
          <desc>
            <address>
              <addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/nancy</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="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.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>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-44647" status="VALID">
          <idno type="anr">ANR-16-CE33-0006</idno>
          <orgName>VOCADOM</orgName>
          <desc>Commande vocale robuste adaptée à la personne et au contexte pour l'autonomie à domicile</desc>
          <date type="start">2016</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>