<?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-03136904</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="2026-05-24T21:07:02+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">GCI Detection from Raw Speech Using a Fully-Convolutional Network</title>
            <author role="aut">
              <persName>
                <forename type="first">Luc</forename>
                <surname>Ardaillon</surname>
              </persName>
              <email type="md5">72a2e9810639b172afb355be6f1769a4</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">luc-ardaillon</idno>
              <idno type="idhal" notation="numeric">6737</idno>
              <idno type="halauthorid" notation="string">28342-6737</idno>
              <idno type="IDREF">https://www.idref.fr/227185943</idno>
              <affiliation ref="#struct-541780"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Axel</forename>
                <surname>Roebel</surname>
              </persName>
              <email type="md5">f5827691d18202684001d3300c088d9c</email>
              <email type="domain">ircam.fr</email>
              <idno type="idhal" notation="string">axel-roebel</idno>
              <idno type="idhal" notation="numeric">4527</idno>
              <idno type="halauthorid" notation="string">20620-4527</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6136-4391</idno>
              <idno type="IDREF">https://www.idref.fr/227186079</idno>
              <idno type="IDREF">https://www.idref.fr/163747032</idno>
              <affiliation ref="#struct-541780"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Axel</forename>
                <surname>Roebel</surname>
              </persName>
              <email type="md5">f5827691d18202684001d3300c088d9c</email>
              <email type="domain">ircam.fr</email>
            </editor>
            <funder ref="#projanr-53413"/>
            <funder ref="#projanr-50412"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-02-10 08:22:55</date>
              <date type="whenModified">2024-10-30 13:28:08</date>
              <date type="whenReleased">2021-02-10 08:22:55</date>
              <date type="whenProduced">2020-05-04</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/1910.10235"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="194979">
                <persName>
                  <forename>Axel</forename>
                  <surname>Roebel</surname>
                </persName>
                <email type="md5">f5827691d18202684001d3300c088d9c</email>
                <email type="domain">ircam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03136904</idno>
            <idno type="halUri">https://hal.science/hal-03136904</idno>
            <idno type="halBibtex">ardaillon:hal-03136904</idno>
            <idno type="halRefHtml">&lt;i&gt;ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)&lt;/i&gt;, May 2020, Barcelona, Spain. pp.6739-6743, &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICASSP40776.2020.9053089"&gt;&amp;#x27E8;10.1109/ICASSP40776.2020.9053089&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, Spain. pp.6739-6743, &amp;#x27E8;10.1109/ICASSP40776.2020.9053089&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="IRCAM">Institut de Recherche et Coordination Acoustique/Musique</idno>
            <idno type="stamp" n="STMS" corresp="SORBONNE-UNIVERSITE">Sciences et technologies de la musique et du son</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">Minor corrections after reviews of ICASSP 2020 (accepted paper). (Corrected typos, added funding aknowledgments, added some references, cleaned bibliography, added a few details)</note>
            <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">GCI Detection from Raw Speech Using a Fully-Convolutional Network</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Luc</forename>
                    <surname>Ardaillon</surname>
                  </persName>
                  <email type="md5">72a2e9810639b172afb355be6f1769a4</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">luc-ardaillon</idno>
                  <idno type="idhal" notation="numeric">6737</idno>
                  <idno type="halauthorid" notation="string">28342-6737</idno>
                  <idno type="IDREF">https://www.idref.fr/227185943</idno>
                  <affiliation ref="#struct-541780"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Axel</forename>
                    <surname>Roebel</surname>
                  </persName>
                  <email type="md5">f5827691d18202684001d3300c088d9c</email>
                  <email type="domain">ircam.fr</email>
                  <idno type="idhal" notation="string">axel-roebel</idno>
                  <idno type="idhal" notation="numeric">4527</idno>
                  <idno type="halauthorid" notation="string">20620-4527</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6136-4391</idno>
                  <idno type="IDREF">https://www.idref.fr/227186079</idno>
                  <idno type="IDREF">https://www.idref.fr/163747032</idno>
                  <affiliation ref="#struct-541780"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title>
                  <date type="start">2020-05-04</date>
                  <date type="end">2020-05-08</date>
                  <settlement>Barcelona</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="serie">IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</biblScope>
                  <biblScope unit="pp">6739-6743</biblScope>
                  <date type="datePub">2020-05-04</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1910.10235</idno>
              <idno type="doi">10.1109/ICASSP40776.2020.9053089</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-sd">Computer Science [cs]/Sound [cs.SD]</classCode>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</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>Glottal Closure Instants (GCI) detection consists in automatically detecting temporal locations of most significant excitation of the vocal tract from the speech signal. It is used in many speech analysis and processing applications, and various algorithms have been proposed for this purpose. Recently, new approaches using convolutional neural networks have emerged, with encouraging results. Following this trend, we propose a simple approach that performs a mapping from the speech waveform to a target signal from which the GCIs are obtained by peak-picking. However, the ground truth GCIs used for training and evaluation are usually extracted from EGG signals, which are not perfectly reliable and often not available. To overcome this problem, we propose to train our network on high-quality synthetic speech with perfect ground truth. The performances of the proposed algorithm are compared with three other state-of-the-art approaches using publicly available datasets, and the impact of using controlled synthetic or real speech signals in the training stage is investigated. The experimental results demonstrate that the proposed method obtains similar or better results than other state-of-the-art algorithms and that using large synthetic datasets with many speakers offers a better generalization ability than using a smaller database of real speech and EGG signals.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-541780" status="VALID">
          <orgName>Analyse et synthèse sonores [Paris]</orgName>
          <desc>
            <address>
              <addrLine>1, place Igor stravinsky, 75004, Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://anasynth.ircam.fr/home/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-541779" type="direct"/>
            <relation active="#struct-5234" type="indirect"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR9912" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-541779" status="VALID">
          <idno type="IdRef">24096277X</idno>
          <idno type="RNSR">198319352N</idno>
          <idno type="ROR">025xvn046</idno>
          <orgName>Sciences et Technologies de la Musique et du Son</orgName>
          <orgName type="acronym">STMS</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>1 Place Igor Stravinsky 75004 PARIS</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ircam.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5234" type="direct"/>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR9912" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-5234" status="VALID">
          <idno type="ROR">https://ror.org/0121jnt59</idno>
          <orgName>Institut de Recherche et Coordination Acoustique/Musique</orgName>
          <orgName type="acronym">IRCAM</orgName>
          <desc>
            <address>
              <addrLine>1, place Igor Stravinsky 75004 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ircam.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.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="anrProject" xml:id="projanr-53413" status="VALID">
          <idno type="anr">ANR-19-CE38-0001</idno>
          <orgName>ARS</orgName>
          <desc>Analyse et transformation du style de chant</desc>
          <date type="start">2019</date>
        </org>
        <org type="anrProject" xml:id="projanr-50412" status="VALID">
          <idno type="anr">ANR-17-CE23-0025</idno>
          <orgName>TheVoice</orgName>
          <desc>DESIGN DE VOIX POUR L'INDUSTRIE CREATIVE</desc>
          <date type="start">2017</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>