<?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-01320119</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="2026-05-13T00:08:48+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Multiple resolution analysis for robust automatic speech recognition</title>
            <author role="aut">
              <persName>
                <forename type="first">Roberto</forename>
                <surname>Gemello</surname>
              </persName>
              <idno type="halauthorid">427506-0</idno>
              <affiliation ref="#struct-23072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Franco</forename>
                <surname>Mana</surname>
              </persName>
              <idno type="halauthorid">427507-0</idno>
              <affiliation ref="#struct-23072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Dario</forename>
                <surname>Albesano</surname>
              </persName>
              <idno type="halauthorid">1030019-0</idno>
              <affiliation ref="#struct-23072"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Renato</forename>
                <surname>de Mori</surname>
              </persName>
              <idno type="halauthorid">496043-0</idno>
              <orgName ref="#struct-195507"/>
              <affiliation ref="#struct-100376"/>
            </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">2016-05-23 14:30:19</date>
              <date type="whenModified">2020-01-14 10:38:06</date>
              <date type="whenReleased">2016-05-23 14:30:19</date>
              <date type="whenProduced">2006-01</date>
              <ref type="externalLink" target="https://api.istex.fr/ark:/67375/6H6-HW612HQD-D/fulltext.pdf?sid=hal"/>
            </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-01320119</idno>
            <idno type="halUri">https://hal.science/hal-01320119</idno>
            <idno type="halBibtex">gemello:hal-01320119</idno>
            <idno type="halRefHtml">&lt;i&gt;Computer Speech and Language&lt;/i&gt;, 2006, &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.csl.2004.06.001"&gt;&amp;#x27E8;10.1016/j.csl.2004.06.001&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Computer Speech and Language, 2006, &amp;#x27E8;10.1016/j.csl.2004.06.001&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </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="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Multiple resolution analysis for robust automatic speech recognition</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Roberto</forename>
                    <surname>Gemello</surname>
                  </persName>
                  <idno type="halauthorid">427506-0</idno>
                  <affiliation ref="#struct-23072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Franco</forename>
                    <surname>Mana</surname>
                  </persName>
                  <idno type="halauthorid">427507-0</idno>
                  <affiliation ref="#struct-23072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Dario</forename>
                    <surname>Albesano</surname>
                  </persName>
                  <idno type="halauthorid">1030019-0</idno>
                  <affiliation ref="#struct-23072"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Renato</forename>
                    <surname>de Mori</surname>
                  </persName>
                  <idno type="halauthorid">496043-0</idno>
                  <orgName ref="#struct-195507"/>
                  <affiliation ref="#struct-100376"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">12036</idno>
                <idno type="issn">0885-2308</idno>
                <idno type="eissn">1095-8363</idno>
                <title level="j">Computer Speech and Language</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <date type="datePub">2006-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.csl.2004.06.001</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper investigates the potential of exploiting the redundancy implicit in multiple resolution analysis for automatic speech recognition systems. The analysis is performed by a binary tree of elements, each one of which is made by a half-band filter followed by a down sampler which discards odd samples. Filter design and feature computation from samples are discussed and recognition performance with different choices is presented. A paradigm consisting in redundant feature extraction, followed by feature normalization, followed by dimensionality reduction is proposed. Feature normalization is performed by denoising algorithms. Two of them are considered and evaluated, namely, signal-to-noise ratio-dependent spectral subtraction and soft thresholding. Dimensionality reduction is performed with principal component analysis. Experiments using telephone corpora and the Aurora3 corpus are reported. They indicate that the proposed paradigm leads to a recognition performance with clean speech, measured in word error rate, marginally superior to the one obtained with perceptual linear prediction coefficients. Nevertheless, performance of the proposed analysis paradigm is significantly superior when used with noisy data and the same denoising algorithm is applied to all the analysis methods, which are compared.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-23072" status="VALID">
          <orgName>LOQUENDO</orgName>
          <orgName type="acronym">LOQUENDO</orgName>
          <desc>
            <address>
              <addrLine>Loquendo S.p.A. Via Valdellatorre, 4 10149 Torino</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://www.loquendo.com/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300928" type="direct"/>
          </listRelation>
        </org>
        <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="institution" xml:id="struct-300928" status="VALID">
          <orgName>LOQUENDO</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>