<?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-00861465</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="2026-05-21T20:50:53+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic Head</title>
            <author role="aut">
              <persName>
                <forename type="first">Jan</forename>
                <surname>Cech</surname>
              </persName>
              <email type="md5">3959996edde07f0e5ee891c019e99044</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">934599</idno>
              <idno type="halauthorid" notation="string">554794-934599</idno>
              <affiliation ref="#struct-44969"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ravi</forename>
                <surname>Mittal</surname>
              </persName>
              <idno type="halauthorid">1135518-0</idno>
              <affiliation ref="#struct-44969"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Antoine</forename>
                <surname>Deleforge</surname>
              </persName>
              <email type="md5">c5f115a825bed9b5eeb4952159270467</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">antoine-deleforge</idno>
              <idno type="idhal" notation="numeric">10056</idno>
              <idno type="halauthorid" notation="string">21220-10056</idno>
              <idno type="IDREF">https://www.idref.fr/184451205</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0339-7472</idno>
              <affiliation ref="#struct-44969"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jordi</forename>
                <surname>Sanchez-Riera</surname>
              </persName>
              <idno type="halauthorid">554787-0</idno>
              <affiliation ref="#struct-44969"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xavier</forename>
                <surname>Alameda-Pineda</surname>
              </persName>
              <email type="md5">dbafe48d626373a5d6677f35638fa63d</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">xavier-alameda-pineda</idno>
              <idno type="idhal" notation="numeric">16186</idno>
              <idno type="halauthorid" notation="string">22576-16186</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5354-1084</idno>
              <idno type="IDREF">https://www.idref.fr/18450919X</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-44969"/>
            </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-44969"/>
            </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-98072"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2013-09-12 17:38:01</date>
              <date type="whenModified">2025-09-27 19:42:59</date>
              <date type="whenReleased">2013-09-15 08:01:29</date>
              <date type="whenProduced">2013-10-15</date>
              <date type="whenEndEmbargoed">2013-09-12</date>
              <ref type="file" target="https://inria.hal.science/hal-00861465v1/document">
                <date notBefore="2013-09-12"/>
              </ref>
              <ref type="annex" subtype="figure" n="1" target="https://inria.hal.science/hal-00861465v1/file/demo.jpg" id="file-861465-613818">
                <date notBefore="2013-09-12"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-00861465v1/file/main_final.pdf" id="file-861465-613819">
                <date notBefore="2013-09-12"/>
              </ref>
              <ref type="externalLink" target="http://cmp.felk.cvut.cz/ftp/articles/cech/Cech-Humanoids-2013.pdf"/>
            </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-00861465</idno>
            <idno type="halUri">https://inria.hal.science/hal-00861465</idno>
            <idno type="halBibtex">cech:hal-00861465</idno>
            <idno type="halRefHtml">&lt;i&gt;Humanoids 2013 - IEEE-RAS International Conference on Humanoid Robots&lt;/i&gt;, IEEE Robotics Society, Oct 2013, Atlanta, GA, United States. pp.203-210, &lt;a target="_blank" href="https://dx.doi.org/10.1109/HUMANOIDS.2013.7029977"&gt;&amp;#x27E8;10.1109/HUMANOIDS.2013.7029977&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Humanoids 2013 - IEEE-RAS International Conference on Humanoid Robots, IEEE Robotics Society, Oct 2013, Atlanta, GA, United States. pp.203-210, &amp;#x27E8;10.1109/HUMANOIDS.2013.7029977&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-861465-613818"/><ref corresp="#file-861465-613819"/></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="UNIV-GRENOBLE1">Université Joseph Fourier - Grenoble I</idno>
            <idno type="stamp" n="UNIV-PMF_GRENOBLE">Université Pierre-Mendès-France - Grenoble II</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="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="UGA-TEST-QUATER">UGA-TEST-QUATER</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="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">Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic Head</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Jan</forename>
                    <surname>Cech</surname>
                  </persName>
                  <email type="md5">3959996edde07f0e5ee891c019e99044</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">934599</idno>
                  <idno type="halauthorid" notation="string">554794-934599</idno>
                  <affiliation ref="#struct-44969"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ravi</forename>
                    <surname>Mittal</surname>
                  </persName>
                  <idno type="halauthorid">1135518-0</idno>
                  <affiliation ref="#struct-44969"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Antoine</forename>
                    <surname>Deleforge</surname>
                  </persName>
                  <email type="md5">c5f115a825bed9b5eeb4952159270467</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">antoine-deleforge</idno>
                  <idno type="idhal" notation="numeric">10056</idno>
                  <idno type="halauthorid" notation="string">21220-10056</idno>
                  <idno type="IDREF">https://www.idref.fr/184451205</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0339-7472</idno>
                  <affiliation ref="#struct-44969"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jordi</forename>
                    <surname>Sanchez-Riera</surname>
                  </persName>
                  <idno type="halauthorid">554787-0</idno>
                  <affiliation ref="#struct-44969"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xavier</forename>
                    <surname>Alameda-Pineda</surname>
                  </persName>
                  <email type="md5">dbafe48d626373a5d6677f35638fa63d</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">xavier-alameda-pineda</idno>
                  <idno type="idhal" notation="numeric">16186</idno>
                  <idno type="halauthorid" notation="string">22576-16186</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5354-1084</idno>
                  <idno type="IDREF">https://www.idref.fr/18450919X</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-44969"/>
                </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-44969"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Humanoids 2013 - IEEE-RAS International Conference on Humanoid Robots</title>
                  <date type="start">2013-10-15</date>
                  <date type="end">2013-10-17</date>
                  <settlement>Atlanta, GA</settlement>
                  <country key="US">United States</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>IEEE Robotics Society</name>
                </respStmt>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">203-210</biblScope>
                  <date type="datePub">2013-09-12</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/HUMANOIDS.2013.7029977</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</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 present a method for detecting and localizing an active speaker, i.e., a speaker that emits a sound, through the fusion between visual reconstruction with a stereoscopic camera pair and sound-source localization with several microphones. Both the cameras and the microphones are embedded into the head of a humanoid robot. The proposed statistical fusion model associates 3D faces of potential speakers with 2D sound directions. The paper has two contributions: (i) a method that discretizes the two-dimensional space of all possible sound directions and that accumulates evidence for each direction by estimating the time difference of arrival (TDOA) over all the microphone pairs, such that all the microphones are used simultaneously and symmetrically and (ii) an audio-visual alignment method that maps 3D visual features onto 2D sound directions and onto TDOAs between microphone pairs. This allows to implicitly represent both sensing modalities into a common audiovisual coordinate frame. Using simulated as well as real data, we quantitatively assess the robustness of the method against noise and reverberations, and we compare it with several other methods. Finally, we describe a real-time implementation using the proposed technique and with a humanoid head embedding four microphones and two cameras: this enables natural human-robot interactive behavior.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-44969" status="OLD">
          <idno type="RNSR">200818261U</idno>
          <orgName>Interpretation and Modelling of Images and Videos</orgName>
          <orgName type="acronym">PERCEPTION</orgName>
          <date type="start">2007-01-01</date>
          <date type="end">2015-12-31</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-24474" type="direct"/>
            <relation active="#struct-3886" type="indirect"/>
            <relation active="#struct-51016" type="indirect"/>
            <relation active="#struct-89889" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" 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="laboratory" xml:id="struct-24474" status="OLD">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">0000 0004 0383 676X</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">2007-01-01</date>
          <date type="end">2015-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment IMAG, CS 40700, F-38058 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ljk.imag.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-3886" type="direct"/>
            <relation active="#struct-51016" type="direct"/>
            <relation active="#struct-89889" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-3886" status="OLD">
          <idno type="IdRef">02640432X</idno>
          <idno type="ROR">https://ror.org/02f7wz369</idno>
          <orgName>Université Pierre Mendès France - Grenoble 2</orgName>
          <orgName type="acronym">UPMF</orgName>
          <date type="end">2015-12-31</date>
          <desc>
            <address>
              <addrLine>BP 47 - 38040 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmf-grenoble.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-51016" status="OLD">
          <idno type="IdRef">026404796</idno>
          <idno type="ROR">https://ror.org/02aj0kh94</idno>
          <orgName>Université Joseph Fourier - Grenoble 1</orgName>
          <orgName type="acronym">UJF</orgName>
          <date type="end">2015-12-31</date>
          <desc>
            <address>
              <addrLine>BP 53 - 38041 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ujf-grenoble.fr/</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="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="europeanProject" xml:id="projeurop-98072" status="INCOMING">
          <desc>98071</desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>