<?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-01393972</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="2026-05-20T06:58:32+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition</title>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>Serizel</surname>
              </persName>
              <email type="md5">79c6facd61845beefd37556383e62ff7</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">romain-serizel</idno>
              <idno type="idhal" notation="numeric">10320</idno>
              <idno type="halauthorid" notation="string">10204-10320</idno>
              <idno type="IDREF">https://www.idref.fr/223797391</idno>
              <affiliation ref="#struct-162010"/>
              <affiliation ref="#struct-27016"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Diego</forename>
                <surname>Giuliani</surname>
              </persName>
              <idno type="halauthorid">475935-0</idno>
              <affiliation ref="#struct-452129"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Romain</forename>
                <surname>Serizel</surname>
              </persName>
              <email type="md5">79c6facd61845beefd37556383e62ff7</email>
              <email type="domain">loria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2016-11-09 14:52:36</date>
              <date type="whenModified">2026-01-19 16:46:18</date>
              <date type="whenReleased">2016-11-10 18:34:48</date>
              <date type="whenProduced">2014-12-07</date>
              <date type="whenEndEmbargoed">2016-11-08</date>
              <ref type="file" target="https://hal.science/hal-01393972v1/document">
                <date notBefore="2016-11-08"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01393972v1/file/14-3.pdf" id="file-1393972-1478168">
                <date notBefore="2016-11-08"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-01393972/document"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="463705">
                <persName>
                  <forename>Romain</forename>
                  <surname>Serizel</surname>
                </persName>
                <email type="md5">79c6facd61845beefd37556383e62ff7</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01393972</idno>
            <idno type="halUri">https://hal.science/hal-01393972</idno>
            <idno type="halBibtex">serizel:hal-01393972</idno>
            <idno type="halRefHtml">&lt;i&gt;2014 IEEE Spoken Language Technology Workshop (SLT 2014)&lt;/i&gt;, Dec 2014, South Lake Tahoe, CA, United States. pp.135-140, &lt;a target="_blank" href="https://dx.doi.org/10.1109/SLT.2014.7078563"&gt;&amp;#x27E8;10.1109/SLT.2014.7078563&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">2014 IEEE Spoken Language Technology Workshop (SLT 2014), Dec 2014, South Lake Tahoe, CA, United States. pp.135-140, &amp;#x27E8;10.1109/SLT.2014.7078563&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1393972-1478168"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="ENST">Ecole Nationale Supérieure des Télécommunications</idno>
            <idno type="stamp" n="TELECOM-PARISTECH" corresp="PARISTECH">Télécom Paris</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="LTCI" corresp="TELECOM-PARISTECH">Laboratoire Traitement et Communication de l'Information</idno>
            <idno type="stamp" n="IDS" corresp="TELECOM-PARISTECH">Département Image, Données, Signal</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</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">Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>Serizel</surname>
                  </persName>
                  <email type="md5">79c6facd61845beefd37556383e62ff7</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">romain-serizel</idno>
                  <idno type="idhal" notation="numeric">10320</idno>
                  <idno type="halauthorid" notation="string">10204-10320</idno>
                  <idno type="IDREF">https://www.idref.fr/223797391</idno>
                  <affiliation ref="#struct-162010"/>
                  <affiliation ref="#struct-27016"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Diego</forename>
                    <surname>Giuliani</surname>
                  </persName>
                  <idno type="halauthorid">475935-0</idno>
                  <affiliation ref="#struct-452129"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">2014 IEEE Spoken Language Technology Workshop (SLT)</title>
                <meeting>
                  <title>2014 IEEE Spoken Language Technology Workshop (SLT 2014)</title>
                  <date type="start">2014-12-07</date>
                  <date type="end">2014-12-10</date>
                  <settlement>South Lake Tahoe, CA</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">135-140</biblScope>
                  <date type="datePub">2014</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/SLT.2014.7078563</idno>
              <ref type="publisher">http://ieeexplore.ieee.org/document/7078563/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">deep neural networks</term>
                <term xml:lang="en"> children's speech recognition</term>
                <term xml:lang="en">automatic speech recognition</term>
                <term xml:lang="en">Vocal tract length normalisation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</classCode>
              <classCode scheme="halDomain" n="info.info-ne">Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]</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 introduces approaches based on vocal tract length normalisation (VTLN) techniques for hybrid deep neural network (DNN)-hidden Markov model (HMM) automatic speech recognition when targeting children's and adults' speech. VTLN is investigated by training a DNN-HMM system by using first mel frequency cepstral coefficients (MFCCs) normalised with standard VTLN. Then, MFCCs derived acoustic features are combined with the VTLN warping factors to obtain an augmented set of features as input to a DNN. In this later, novel, approach the warping factors are obtained with a separate DNN and the decoding can be operated in a single pass when standard VTLN approach requires two decoding passes. Both VTLN-based approaches are shown to improve phone error rate performance, up to 20% relative improvement, compared to a baseline trained on a mixture of children's and adults' speech.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-162010" status="OLD">
          <orgName>Laboratoire Traitement et Communication de l'Information</orgName>
          <orgName type="acronym">LTCI</orgName>
          <desc>
            <address>
              <addrLine>46 rue Barrault F-75634 Paris Cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ltci.telecom-paristech.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300362" type="direct"/>
            <relation active="#struct-302102" type="direct"/>
            <relation name="UMR5141" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-27016" status="OLD">
          <orgName>Département Traitement du Signal et des Images</orgName>
          <orgName type="acronym">TSI</orgName>
          <date type="start">2008-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>Télécom ParisTech / TSI 46, rue Barrault 75634 PARIS Cedex 13</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-300362" type="direct"/>
            <relation name="UMR5141" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-452129" status="VALID">
          <idno type="ROR">https://ror.org/01j33xk10</idno>
          <orgName>Fondazione Bruno Kessler [Trento, Italy]</orgName>
          <orgName type="acronym">FBK</orgName>
          <desc>
            <address>
              <addrLine>via Santa Croce, 77 - 38122 Trento</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.fbk.eu/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300362" status="VALID">
          <idno type="ROR">https://ror.org/01naq7912</idno>
          <orgName>Télécom ParisTech</orgName>
          <date type="start">2008-01-01</date>
          <date type="end">2019-06-11</date>
          <desc>
            <address>
              <addrLine>46 rue Barrault 75634 Paris Cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.telecom-paris.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.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>
    </back>
  </text>
</TEI>