<?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-01350071</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="2026-05-03T19:27:13+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">OCR-aided person annotation and label propagation for speaker modeling in TV shows</title>
            <author role="aut">
              <persName>
                <forename type="first">Mateusz</forename>
                <surname>Budnik</surname>
              </persName>
              <idno type="halauthorid">836350-0</idno>
              <affiliation ref="#struct-1041964"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Besacier</surname>
              </persName>
              <email type="md5">30912a0f36556a3d42939f031801b653</email>
              <email type="domain">imag.fr</email>
              <idno type="idhal" notation="string">laurent-besacier</idno>
              <idno type="idhal" notation="numeric">1521</idno>
              <idno type="halauthorid" notation="string">7533-1521</idno>
              <idno type="IDREF">https://www.idref.fr/079377017</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7411-9125</idno>
              <affiliation ref="#struct-1041971"/>
              <affiliation ref="#struct-56663"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ali</forename>
                <surname>Khodabakhsh</surname>
              </persName>
              <idno type="halauthorid">1049156-0</idno>
              <affiliation ref="#struct-1041964"/>
              <affiliation ref="#struct-495165"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cenk</forename>
                <surname>Demiroglu</surname>
              </persName>
              <idno type="halauthorid">1049157-0</idno>
              <affiliation ref="#struct-495165"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Laurent</forename>
                <surname>Besacier</surname>
              </persName>
              <email type="md5">30912a0f36556a3d42939f031801b653</email>
              <email type="domain">imag.fr</email>
            </editor>
            <funder ref="#projanr-35535"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2016-07-29 15:34:47</date>
              <date type="whenModified">2025-09-27 19:09:00</date>
              <date type="whenReleased">2016-08-02 14:00:34</date>
              <date type="whenProduced">2016-03</date>
              <date type="whenEndEmbargoed">2016-07-29</date>
              <ref type="file" target="https://hal.science/hal-01350071v1/document">
                <date notBefore="2016-07-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01350071v1/file/ocr-aided-person-4.pdf" id="file-1350071-1431484">
                <date notBefore="2016-07-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="192664">
                <persName>
                  <forename>Laurent</forename>
                  <surname>Besacier</surname>
                </persName>
                <email type="md5">30912a0f36556a3d42939f031801b653</email>
                <email type="domain">imag.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01350071</idno>
            <idno type="halUri">https://hal.science/hal-01350071</idno>
            <idno type="halBibtex">budnik:hal-01350071</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE ICASSP 2016&lt;/i&gt;, Mar 2016, Shangai, China. &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICASSP.2016.7472743"&gt;&amp;#x27E8;10.1109/ICASSP.2016.7472743&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE ICASSP 2016, Mar 2016, Shangai, China. &amp;#x27E8;10.1109/ICASSP.2016.7472743&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1350071-1431484"/></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="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="LIG">Laboratoire d'Informatique de Grenoble</idno>
            <idno type="stamp" n="LIG_TDCGE_GETALP" corresp="LIG_TDCGE">GETALP</idno>
            <idno type="stamp" n="LIG_TDCGE_MRIM" corresp="LIG_TDCGE">MRIM</idno>
            <idno type="stamp" n="POLYTECH-GRENOBLE">Polytech Grenoble</idno>
            <idno type="stamp" n="UGA-COMUE">Université Grenoble Alpes [2016-2019]</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="LIG_SIDCH" corresp="LIG">Systèmes intelligents pour les données, les connaissances et les humains</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">OCR-aided person annotation and label propagation for speaker modeling in TV shows</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mateusz</forename>
                    <surname>Budnik</surname>
                  </persName>
                  <idno type="halauthorid">836350-0</idno>
                  <affiliation ref="#struct-1041964"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Besacier</surname>
                  </persName>
                  <email type="md5">30912a0f36556a3d42939f031801b653</email>
                  <email type="domain">imag.fr</email>
                  <idno type="idhal" notation="string">laurent-besacier</idno>
                  <idno type="idhal" notation="numeric">1521</idno>
                  <idno type="halauthorid" notation="string">7533-1521</idno>
                  <idno type="IDREF">https://www.idref.fr/079377017</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7411-9125</idno>
                  <affiliation ref="#struct-1041971"/>
                  <affiliation ref="#struct-56663"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ali</forename>
                    <surname>Khodabakhsh</surname>
                  </persName>
                  <idno type="halauthorid">1049156-0</idno>
                  <affiliation ref="#struct-1041964"/>
                  <affiliation ref="#struct-495165"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cenk</forename>
                    <surname>Demiroglu</surname>
                  </persName>
                  <idno type="halauthorid">1049157-0</idno>
                  <affiliation ref="#struct-495165"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) </title>
                <meeting>
                  <title>IEEE ICASSP 2016</title>
                  <date type="start">2016-03</date>
                  <settlement>Shangai</settlement>
                  <country key="CN">China</country>
                </meeting>
                <imprint>
                  <date type="datePub">2016</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICASSP.2016.7472743</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">OCR</term>
                <term xml:lang="en">speaker identification</term>
                <term xml:lang="en">clustering</term>
                <term xml:lang="en">annotation propagation</term>
                <term xml:lang="en">active learning</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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 an approach for minimizing human effort in manual speaker annotation. Label propagation is used at each iteration of an active learning cycle. More precisely, a selection strategy for choosing the most suitable speech track to be labeled is proposed. Four different selection strategies are evaluated and all the tracks in a corresponding cluster are gathered using agglomerative clustering in order to propagate human annotations. To further reduce the manual labor required, an optical character recognition system is used to bootstrap annotations. At each step of the cycle , annotations are used to build speaker models. The quality of the generated speaker models is evaluated at each step using an i-vector based speaker identification system. The presented approach shows promising results on the REPERE corpus with a minimum amount of human effort for annotation .</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1041964" status="OLD">
          <idno type="IdRef">148425550</idno>
          <idno type="ISNI">0000 0001 2286 4035</idno>
          <idno type="RNSR">200711886U</idno>
          <idno type="ROR">https://ror.org/01c8rcg82</idno>
          <orgName>Laboratoire d'Informatique de Grenoble</orgName>
          <orgName type="acronym">LIG</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>UMR 5217 - Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d’Hères Adresse postale : CS 40700 - 38058 Grenoble cedex 9Tél. : 04 57 42 14 00</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.liglab.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-89889" type="direct"/>
            <relation name="UMR5217" active="#struct-441569" type="direct"/>
            <relation active="#struct-445543" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1041971" status="OLD">
          <orgName>Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole</orgName>
          <orgName type="acronym">GETALP</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lig-getalp.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1041964" type="direct"/>
            <relation active="#struct-89889" type="indirect"/>
            <relation name="UMR5217" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-56663" status="VALID">
          <idno type="IdRef">03442945X</idno>
          <idno type="ISNI">0000000119314817</idno>
          <idno type="ROR">https://ror.org/055khg266</idno>
          <idno type="Wikidata">Q1665127</idno>
          <orgName>Institut universitaire de France</orgName>
          <orgName type="acronym">IUF</orgName>
          <desc>
            <address>
              <addrLine>Maison des Universités 103 Boulevard Saint-Michel 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://iuf.amue.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301855" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-495165" status="VALID">
          <idno type="ROR">https://ror.org/03a5qrr21</idno>
          <orgName>Istanbul University</orgName>
          <date type="start">1453-05-30</date>
          <desc>
            <address>
              <addrLine>Istanbul University Main Campus34452 Beyazit/Fatih-Istanbul</addrLine>
              <country key="TR"/>
            </address>
            <ref type="url">https://www.istanbul.edu.tr/tr/_</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>
        <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="institution" xml:id="struct-301855" status="VALID">
          <orgName>Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche</orgName>
          <orgName type="acronym">M.E.N.E.S.R.</orgName>
          <desc>
            <address>
              <addrLine>1 rue Descartes - 75231 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-35535" status="VALID">
          <idno type="anr">ANR-12-CHRI-0006</idno>
          <idno type="program">Recherche Européenne Coordonnée sur les Défis à Long-terme dans les Sciences et Technologies de l'Information et de la Communication</idno>
          <orgName>CAMOMILE</orgName>
          <desc>Annotation collaborative de documents multi-modaux, multi-lingues et multi-média</desc>
          <date type="start">2012</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>