<?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-04623038</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="2026-05-14T06:13:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">SUMM-RE: A corpus of French meeting-style conversations</title>
            <title xml:lang="fr">Nous présentons le corpus SUMM-RE un ensemble de données d’environ 95 heures de conversations spontanées de type réunion en français</title>
            <author role="aut">
              <persName>
                <forename type="first">Julie</forename>
                <surname>Hunter</surname>
              </persName>
              <idno type="halauthorid">489211-0</idno>
              <affiliation ref="#struct-238942"/>
              <affiliation ref="#struct-356171"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hiroyoshi</forename>
                <surname>Yamasaki</surname>
              </persName>
              <idno type="halauthorid">3022375-0</idno>
              <affiliation ref="#struct-199923"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Océane</forename>
                <surname>Granier</surname>
              </persName>
              <idno type="halauthorid">2120313-0</idno>
              <affiliation ref="#struct-199923"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jérôme</forename>
                <surname>Louradour</surname>
              </persName>
              <idno type="halauthorid">431511-0</idno>
              <affiliation ref="#struct-238942"/>
              <affiliation ref="#struct-356171"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Roxane</forename>
                <surname>Bertrand</surname>
              </persName>
              <email type="md5">a92fd4af8b532b582ffec386a89402d2</email>
              <email type="domain">univ-amu.fr</email>
              <idno type="idhal" notation="string">roxane-bertrand</idno>
              <idno type="idhal" notation="numeric">10347</idno>
              <idno type="halauthorid" notation="string">50959-10347</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0448-5506</idno>
              <idno type="IDREF">https://www.idref.fr/188159053</idno>
              <affiliation ref="#struct-199923"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kate</forename>
                <surname>Thompson</surname>
              </persName>
              <idno type="halauthorid">1735408-0</idno>
              <affiliation ref="#struct-238942"/>
              <affiliation ref="#struct-356171"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Prévot</surname>
              </persName>
              <email type="md5">4c9059c11334ca67edc05af6cdf735a8</email>
              <email type="domain">univ-amu.fr</email>
              <idno type="idhal" notation="string">laurent-prevot</idno>
              <idno type="idhal" notation="numeric">2580</idno>
              <idno type="halauthorid" notation="string">411514-2580</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2463-2382</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=xxXNsDgAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/078457874</idno>
              <affiliation ref="#struct-56663"/>
              <affiliation ref="#struct-199923"/>
              <affiliation ref="#struct-262992"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Matthieu</forename>
                <surname>Labeau</surname>
              </persName>
              <email type="md5">3414152dcb8870e2d10b4ccfe4cdc5f2</email>
              <email type="domain">telecom-paris.fr</email>
            </editor>
            <funder ref="#projanr-52217"/>
            <funder ref="#projanr-42476"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-07-01 09:14:05</date>
              <date type="whenModified">2026-04-22 09:37:40</date>
              <date type="whenReleased">2024-07-01 11:38:14</date>
              <date type="whenProduced">2024-07-08</date>
              <date type="whenEndEmbargoed">2024-07-01</date>
              <ref type="file" target="https://inria.hal.science/hal-04623038v1/document">
                <date notBefore="2024-07-01"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://inria.hal.science/hal-04623038v1/file/9633.pdf" id="file-4629984-4019297">
                <date notBefore="2024-07-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="850749">
                <persName>
                  <forename>Matthieu</forename>
                  <surname>Labeau</surname>
                </persName>
                <email type="md5">3414152dcb8870e2d10b4ccfe4cdc5f2</email>
                <email type="domain">telecom-paris.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04623038</idno>
            <idno type="halUri">https://inria.hal.science/hal-04623038</idno>
            <idno type="halBibtex">hunter:hal-04623038</idno>
            <idno type="halRefHtml">&lt;i&gt;35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024)&lt;/i&gt;, Jul 2024, Toulouse, France. pp.508-529</idno>
            <idno type="halRef">35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), Jul 2024, Toulouse, France. pp.508-529</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4629984-4019297"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-AMU">Aix Marseille Université</idno>
            <idno type="stamp" n="LPL-AIX">Laboratoire Parole et Langage</idno>
            <idno type="stamp" n="CAMPUS-AAR">Campus-AAR</idno>
            <idno type="stamp" n="AAI">Collection LaCAS - Open Archives in Language and Cultural Area Studies</idno>
            <idno type="stamp" n="ILCB">Institut Langage, Communication et Cerveau</idno>
            <idno type="stamp" n="TALN-RECITAL">Conférences TALN RECITAL</idno>
            <idno type="stamp" n="ASIES_ET_PACIFIQUE">Études aréales - Asies et Pacifique</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="JEP-TALN-RECITAL2024" corresp="TALN-RECITAL">CONFÉRENCE JEP TALN RECITAL 2024</idno>
            <idno type="stamp" n="ANR-IA-20" corresp="ANR-IA">ANR-IA-20</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="3">National</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">SUMM-RE: A corpus of French meeting-style conversations</title>
                <title xml:lang="fr">Nous présentons le corpus SUMM-RE un ensemble de données d’environ 95 heures de conversations spontanées de type réunion en français</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Julie</forename>
                    <surname>Hunter</surname>
                  </persName>
                  <idno type="halauthorid">489211-0</idno>
                  <affiliation ref="#struct-238942"/>
                  <affiliation ref="#struct-356171"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hiroyoshi</forename>
                    <surname>Yamasaki</surname>
                  </persName>
                  <idno type="halauthorid">3022375-0</idno>
                  <affiliation ref="#struct-199923"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Océane</forename>
                    <surname>Granier</surname>
                  </persName>
                  <idno type="halauthorid">2120313-0</idno>
                  <affiliation ref="#struct-199923"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jérôme</forename>
                    <surname>Louradour</surname>
                  </persName>
                  <idno type="halauthorid">431511-0</idno>
                  <affiliation ref="#struct-238942"/>
                  <affiliation ref="#struct-356171"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Roxane</forename>
                    <surname>Bertrand</surname>
                  </persName>
                  <email type="md5">a92fd4af8b532b582ffec386a89402d2</email>
                  <email type="domain">univ-amu.fr</email>
                  <idno type="idhal" notation="string">roxane-bertrand</idno>
                  <idno type="idhal" notation="numeric">10347</idno>
                  <idno type="halauthorid" notation="string">50959-10347</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0448-5506</idno>
                  <idno type="IDREF">https://www.idref.fr/188159053</idno>
                  <affiliation ref="#struct-199923"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kate</forename>
                    <surname>Thompson</surname>
                  </persName>
                  <idno type="halauthorid">1735408-0</idno>
                  <affiliation ref="#struct-238942"/>
                  <affiliation ref="#struct-356171"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Prévot</surname>
                  </persName>
                  <email type="md5">4c9059c11334ca67edc05af6cdf735a8</email>
                  <email type="domain">univ-amu.fr</email>
                  <idno type="idhal" notation="string">laurent-prevot</idno>
                  <idno type="idhal" notation="numeric">2580</idno>
                  <idno type="halauthorid" notation="string">411514-2580</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2463-2382</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=xxXNsDgAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/078457874</idno>
                  <affiliation ref="#struct-56663"/>
                  <affiliation ref="#struct-199923"/>
                  <affiliation ref="#struct-262992"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">35èmes Journées d'Études sur la Parole (JEP 2024)</title>
                <meeting>
                  <title>35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024)</title>
                  <date type="start">2024-07-08</date>
                  <date type="end">2024-07-12</date>
                  <settlement>Toulouse</settlement>
                  <country key="FR">France</country>
                </meeting>
                <editor>BALAGUER</editor>
                <editor>Mathieu and BENDAHMAN</editor>
                <editor>Nihed and HO-DAC</editor>
                <editor>Lydia-Mai and MAUCLAIR</editor>
                <editor>Julie and MORENO</editor>
                <editor>Jose G and PINQUIER</editor>
                <editor>Julien</editor>
                <imprint>
                  <publisher>ATALA &amp; AFPC</publisher>
                  <biblScope unit="volume">1 : articles longs et prises de position</biblScope>
                  <biblScope unit="pp">508-529</biblScope>
                  <date type="datePub">2024</date>
                </imprint>
              </monogr>
              <relatedItem target="https://inria.hal.science/hal-04623005v1" type="IsPartOf" subtype="http://purl.org/coar/resource_type/c_18cf"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Dialogue</term>
                <term xml:lang="en">Transcription</term>
                <term xml:lang="en">French</term>
                <term xml:lang="en">Spontaneous conversation</term>
                <term xml:lang="en">Meetings</term>
                <term xml:lang="en">Corpus</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>We present the SUMM-RE corpus, a dataset of roughly 95 hours of spontaneous meeting-style conversations in French. The corpus is designed to serve as a foundation for downstream tasks such as meeting summarization. In its current state, it offers 25 hours of manually corrected transcripts that are aligned with the audio signal, making it a valuable resource for evaluating ASR and speaker recognition systems. It also includes automatic transcripts and alignments of the whole corpus which can be used for downstream NLP tasks. The aim of this paper is to describe the conception, production and annotation of the corpus up to the transcription level as well as to provide statistics that shed light on the main linguistic features of the corpus.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-238942" status="VALID">
          <orgName>Linagora Labs [Toulouse]</orgName>
          <desc>
            <address>
              <addrLine>Toulouse, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://research.linagora.com</ref>
          </desc>
          <listRelation>
            <relation active="#struct-356171" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-356171" status="VALID">
          <orgName>Linagora [Puteaux]</orgName>
          <desc>
            <address>
              <addrLine>74/80 Roque de Fillol Street92800 Puteaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.linagora.com</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-199923" status="VALID">
          <idno type="IdRef">166744573</idno>
          <idno type="RNSR">201220301U</idno>
          <idno type="ROR">05whq8x35</idno>
          <orgName>Laboratoire Parole et Langage</orgName>
          <orgName type="acronym">LPL</orgName>
          <date type="start">1976-01-01</date>
          <desc>
            <address>
              <addrLine>Laboratoire Parole et LangageCNRS - Aix Marseille Université5 avenue Pasteur13100 Aix-en-Provence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lpl-aix.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-198056" type="direct"/>
            <relation name="UMR7309 / UMR6057 / ESA6057 / ERS164 /  URA261" active="#struct-441569" type="direct"/>
          </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="laboratory" xml:id="struct-262992" status="VALID">
          <orgName>Centre d'études français sur la Chine contemporaine</orgName>
          <orgName type="acronym">CEFC</orgName>
          <desc>
            <address>
              <addrLine>Room 3029, Academic Building, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR China</addrLine>
              <country key="HK"/>
            </address>
            <ref type="url">http://www.cefc.com.hk</ref>
          </desc>
          <listRelation>
            <relation active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-198056" status="VALID">
          <idno type="IdRef">15863621X</idno>
          <idno type="ISNI">0000 0001 2176 4817</idno>
          <idno type="ROR">https://ror.org/035xkbk20</idno>
          <orgName>Aix Marseille Université</orgName>
          <orgName type="acronym">AMU</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Aix-Marseille UniversitéJardins du Pharo58 Boulevard Charles Livon13284 Marseille cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-amu.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-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-52217" status="VALID">
          <idno type="anr">ANR-20-CE23-0017</idno>
          <orgName>SUMM-RE</orgName>
          <desc>Supervision Distante pour les Compte-Rendus Enrichis de Relations Rhétoriques</desc>
          <date type="start">2020</date>
        </org>
        <org type="anrProject" xml:id="projanr-42476" status="VALID">
          <idno type="anr">ANR-16-CONV-0002</idno>
          <orgName>ILCB</orgName>
          <desc>ILCB: Institute of Language Communication and the Brain</desc>
          <date type="start">2016</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>