<?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-01318077</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="2026-05-03T22:09:56+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Détection de mots hors-vocabulaire par combinaison de mesures de confiance de haut et bas niveaux</title>
            <author role="aut">
              <persName>
                <forename type="first">Benjamin</forename>
                <surname>Lecouteux</surname>
              </persName>
              <email type="md5">00fb85dccaa8e3aee7df247b61e55daf</email>
              <email type="domain">imag.fr</email>
              <idno type="idhal" notation="string">benjamin-lecouteux</idno>
              <idno type="idhal" notation="numeric">7847</idno>
              <idno type="halauthorid" notation="string">36516-7847</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ZwqCxusAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/135355060</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3000-6190</idno>
              <affiliation ref="#struct-100376"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Georges</forename>
                <surname>Linares</surname>
              </persName>
              <email type="md5">02dfb19dd98def9dfd333f988de16a6e</email>
              <email type="domain">univ-avignon.fr</email>
              <idno type="idhal" notation="string">georges-linares</idno>
              <idno type="idhal" notation="numeric">4977</idno>
              <idno type="halauthorid" notation="string">14734-4977</idno>
              <idno type="IDREF">https://www.idref.fr/079368794</idno>
              <affiliation ref="#struct-100376"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Benoit</forename>
                <surname>Favre</surname>
              </persName>
              <email type="md5">30e14145e82a7f68e178947a4cb2d7c2</email>
              <email type="domain">lis-lab.fr</email>
              <idno type="idhal" notation="string">benoit-favre</idno>
              <idno type="idhal" notation="numeric">4978</idno>
              <idno type="halauthorid" notation="string">435021-4978</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9777-4613</idno>
              <idno type="IDREF">https://www.idref.fr/115288511</idno>
              <affiliation ref="#struct-159394"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>bibliothèque Universitaire</forename>
                <surname>Déposants HAL-Avignon</surname>
              </persName>
              <email type="md5">3011b28d63fd8bc24593f3121e933912</email>
              <email type="domain">univ-avignon.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-11-09 09:14:12</date>
              <date type="whenModified">2022-01-21 15:44:03</date>
              <date type="whenReleased">2017-11-09 14:00:07</date>
              <date type="whenProduced">2009-11</date>
              <date type="whenEndEmbargoed">2017-11-09</date>
              <ref type="file" target="https://hal.science/hal-01318077v1/document">
                <date notBefore="2017-11-09"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01318077v1/file/1522%281%29.pdf" id="file-1631320-1676877">
                <date notBefore="2017-11-09"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="440719">
                <persName>
                  <forename>bibliothèque Universitaire</forename>
                  <surname>Déposants HAL-Avignon</surname>
                </persName>
                <email type="md5">3011b28d63fd8bc24593f3121e933912</email>
                <email type="domain">univ-avignon.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01318077</idno>
            <idno type="halUri">https://hal.science/hal-01318077</idno>
            <idno type="halBibtex">lecouteux:hal-01318077</idno>
            <idno type="halRefHtml">&lt;i&gt;MajecSTIC 2009 &lt;/i&gt;, Nov 2009, Avignon, France</idno>
            <idno type="halRef">MajecSTIC 2009 , Nov 2009, Avignon, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1631320-1676877"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-AVIGNON">Université d'Avignon</idno>
            <idno type="stamp" n="LIA" corresp="UNIV-AVIGNON">Laboratoire Informatique d'Avignon</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">Détection de mots hors-vocabulaire par combinaison de mesures de confiance de haut et bas niveaux</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Benjamin</forename>
                    <surname>Lecouteux</surname>
                  </persName>
                  <email type="md5">00fb85dccaa8e3aee7df247b61e55daf</email>
                  <email type="domain">imag.fr</email>
                  <idno type="idhal" notation="string">benjamin-lecouteux</idno>
                  <idno type="idhal" notation="numeric">7847</idno>
                  <idno type="halauthorid" notation="string">36516-7847</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ZwqCxusAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/135355060</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3000-6190</idno>
                  <affiliation ref="#struct-100376"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Georges</forename>
                    <surname>Linares</surname>
                  </persName>
                  <email type="md5">02dfb19dd98def9dfd333f988de16a6e</email>
                  <email type="domain">univ-avignon.fr</email>
                  <idno type="idhal" notation="string">georges-linares</idno>
                  <idno type="idhal" notation="numeric">4977</idno>
                  <idno type="halauthorid" notation="string">14734-4977</idno>
                  <idno type="IDREF">https://www.idref.fr/079368794</idno>
                  <affiliation ref="#struct-100376"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Benoit</forename>
                    <surname>Favre</surname>
                  </persName>
                  <email type="md5">30e14145e82a7f68e178947a4cb2d7c2</email>
                  <email type="domain">lis-lab.fr</email>
                  <idno type="idhal" notation="string">benoit-favre</idno>
                  <idno type="idhal" notation="numeric">4978</idno>
                  <idno type="halauthorid" notation="string">435021-4978</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9777-4613</idno>
                  <idno type="IDREF">https://www.idref.fr/115288511</idno>
                  <affiliation ref="#struct-159394"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>MajecSTIC 2009 </title>
                  <date type="start">2009-11</date>
                  <settlement>Avignon</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <date type="datePub">2009-03-16</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en"> speech recognition</term>
                <term xml:lang="en"> confidence measures</term>
                <term xml:lang="en">confidence measures</term>
                <term xml:lang="en">OOV word detection</term>
                <term xml:lang="fr"> reconnaissance automa-</term>
                <term xml:lang="fr"> mesures de confiance</term>
                <term xml:lang="fr">Détection des mots hors-vocabulaire</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>This paper addresses the issue of Out-Of-Vocabulary (OOV) word detection in Large Vocabulary Continuous Speech Recognition (LVCSR) systems. We propose a method inspired by confidence measures, that consists in analyzing the recognition system outputs in order to automatically detect errors due to OOV words. This method combines various features based on acoustic, linguistic , decoding graph and semantics. We evaluate separately each feature and we estimate their complementarity. Experiments are conducted on a large French broadcast news corpus from the ESTER evaluation campaign. Results show good performance in real conditions : the method obtains an OOV word detection rate of 43%-90% with 2.5%-17.5% of false detection. </p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Cet article aborde le problème de la détection des mots hors-vocabulaire dans le cadre des Sys-tèmes de Reconnaissance Automatique de la Parole (SRAP) continu grand vocabulaire. Nous pro-posons une méthode inspirée par les mesures de confiance, qui consiste en l'analyse des sorties du système afin d'y détecter automatiquement les erreurs liées aux mots hors-vocabulaire. Cette méthode combine différents paramètres basés sur l'acoustique, la linguistique, la topologie du graphe de décodage ainsi que sur des paramètres sémantiques. Nous évaluons séparément cha-cun de ces paramètres et nous estimons leur complémentarité. Les expériences ont été menées sur un corpus d'émissions radio issu de la campagne ESTER. Les résultats montrent des performances intéressantes en condition réelle : nous obtenons un taux de détection de mots hors vocabulaire de 43%-90% pour 2.5%-17.5% de fausse détection. </p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-100376" status="VALID">
          <orgName>Laboratoire Informatique d'Avignon</orgName>
          <orgName type="acronym">LIA</orgName>
          <desc>
            <address>
              <addrLine>339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lia.univ-avignon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-195507" type="direct"/>
            <relation active="#struct-302221" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-159394" status="VALID">
          <orgName>International Computer Science Institute [Berkeley]</orgName>
          <orgName type="acronym">ICSI</orgName>
          <desc>
            <address>
              <addrLine>1947 Center Street, Ste. 600 Berkeley, CA 94704</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.icsi.berkeley.edu/icsi/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-320051" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-195507" status="VALID">
          <idno type="ROR">https://ror.org/00mfpxb84</idno>
          <orgName>Avignon Université</orgName>
          <orgName type="acronym">AU</orgName>
          <desc>
            <address>
              <addrLine>74 rue Louis Pasteur - 84 029 Avignon cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-avignon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302221" status="VALID">
          <orgName>Centre d'Enseignement et de Recherche en Informatique - CERI</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-320051" status="INCOMING">
          <orgName>International Computer Science Institute</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>