<?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-01799809</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="2026-05-19T12:19:59+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Multichannel Speech Separation and Enhancement Using the Convolutive Transfer Function</title>
            <author role="aut">
              <persName>
                <forename type="first">Xiaofei</forename>
                <surname>Li</surname>
              </persName>
              <idno type="halauthorid">918557-0</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"/>
              <affiliation ref="#struct-1042500"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sharon</forename>
                <surname>Gannot</surname>
              </persName>
              <idno type="halauthorid">918558-0</idno>
              <affiliation ref="#struct-303955"/>
            </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>Perception</forename>
                <surname>team</surname>
              </persName>
              <email type="md5">dbafe48d626373a5d6677f35638fa63d</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projeurop-98080"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-03-01 17:26:04</date>
              <date type="whenModified">2025-09-27 19:47:01</date>
              <date type="whenReleased">2019-03-01 17:48:45</date>
              <date type="whenProduced">2019-03-01</date>
              <date type="whenEndEmbargoed">2019-03-01</date>
              <ref type="file" target="https://inria.hal.science/hal-01799809v1/document">
                <date notBefore="2019-03-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01799809v1/file/bss_mint.pdf" id="file-2054279-2059659">
                <date notBefore="2019-03-01"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1711.07911"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="160707">
                <persName>
                  <forename>Perception</forename>
                  <surname>team</surname>
                </persName>
                <email type="md5">dbafe48d626373a5d6677f35638fa63d</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01799809</idno>
            <idno type="halUri">https://inria.hal.science/hal-01799809</idno>
            <idno type="halBibtex">li:hal-01799809</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE/ACM Transactions on Audio, Speech and Language Processing&lt;/i&gt;, 2019, 27 (3), pp.645-659. &lt;a target="_blank" href="https://dx.doi.org/10.1109/TASLP.2019.2892412"&gt;&amp;#x27E8;10.1109/TASLP.2019.2892412&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019, 27 (3), pp.645-659. &amp;#x27E8;10.1109/TASLP.2019.2892412&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2054279-2059659"/></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="INRIAARTDOI">INRIAARTDOI</idno>
            <idno type="stamp" n="INRIA-ISRAEL">COPUBLICATION INRIA ISRAEL</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Multichannel Speech Separation and Enhancement Using the Convolutive Transfer Function</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Xiaofei</forename>
                    <surname>Li</surname>
                  </persName>
                  <idno type="halauthorid">918557-0</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"/>
                  <affiliation ref="#struct-1042500"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sharon</forename>
                    <surname>Gannot</surname>
                  </persName>
                  <idno type="halauthorid">918558-0</idno>
                  <affiliation ref="#struct-303955"/>
                </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>
                <idno type="halJournalId" status="VALID">95999</idno>
                <idno type="issn">2329-9290</idno>
                <idno type="eissn">2329-9304</idno>
                <title level="j">IEEE/ACM Transactions on Audio, Speech and Language Processing</title>
                <imprint>
                  <publisher>Institute of Electrical and Electronics Engineers</publisher>
                  <biblScope unit="volume">27</biblScope>
                  <biblScope unit="issue">3</biblScope>
                  <biblScope unit="pp">645-659</biblScope>
                  <date type="datePub">2019-03-01</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1711.07911</idno>
              <idno type="doi">10.1109/TASLP.2019.2892412</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Lasso optimization</term>
                <term xml:lang="en">MINT</term>
                <term xml:lang="en">convolutive transfer function</term>
                <term xml:lang="en">short-time Fourier transform</term>
                <term xml:lang="en">speech enhancement</term>
                <term xml:lang="en">Index Terms-Audio source separation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ts">Computer Science [cs]/Signal and Image Processing</classCode>
              <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="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper addresses the problem of speech separation and enhancement from multichannel convolutive and noisy mixtures, \emph{assuming known mixing filters}. We propose to perform the speech separation and enhancement task in the short-time Fourier transform domain, using the convolutive transfer function (CTF) approximation. Compared to time-domain filters, CTF has much less taps, consequently it has less near-common zeros among channels and less computational complexity. The work proposes three speech-source recovery methods, namely: i) the multichannel inverse filtering method, i.e. the multiple input/output inverse theorem (MINT), is exploited in the CTF domain, and for the multi-source case, ii) a beamforming-like multichannel inverse filtering method applying single source MINT and using power minimization, which is suitable whenever the source CTFs are not all known, and iii) a constrained Lasso method, where the sources are recovered by minimizing the $\ell_1$-norm to impose their spectral sparsity, with the constraint that the $\ell_2$-norm fitting cost, between the microphone signals and the mixing model involving the unknown source signals, is less than a tolerance. The noise can be reduced by setting a tolerance onto the noise power. Experiments under various acoustic conditions are carried out to evaluate the three proposed methods. The comparison between them as well as with the baseline methods is presented.</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="institution" xml:id="struct-303955" status="VALID">
          <idno type="ROR">https://ror.org/03kgsv495</idno>
          <orgName>Bar-Ilan University [Israël]</orgName>
          <desc>
            <address>
              <addrLine>Ramat-Gan 5290002,Israel</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">http://www1.biu.ac.il/indexE.php</ref>
          </desc>
        </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>