Frequency and Wavelet Filtering for Robust Speech Recognition
Identifieur interne : 007A54 ( Main/Exploration ); précédent : 007A53; suivant : 007A55Frequency and Wavelet Filtering for Robust Speech Recognition
Auteurs : Murat Deviren [France] ; Khalid Daoudi [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ]
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Base de données, Intelligence artificielle.
English descriptors
- KwdEn :
Abstract
Abstract: Mel-frequency cepstral coefficients (MFCC) are the most widely used features in current speech recognition systems. However, they have a poor physical interpretation and they do not lie in the frequency domain. Frequency filtering (FF) is a technique that has been recently developed to design frequency-localized speech features that perform similar to MFCC in terms of recognition performances. Motivated by our desire to build time-frequency speech models, we wanted to use the FF technique as front-end. However, when evaluating FF on the Aurora-3 database we found some discrepancies in the highly mismatch case. This led us to put FF in another perspective: the wavelet transform. By doing so, we were able to explain the discrepancies and to achieve significant improvements in recognition in the highly mismatch case.
Url:
DOI: 10.1007/3-540-44989-2_54
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002149
- to stream Istex, to step Curation: 002121
- to stream Istex, to step Checkpoint: 001A44
- to stream Main, to step Merge: 007E33
- to stream PascalFrancis, to step Corpus: 000727
- to stream PascalFrancis, to step Curation: 000314
- to stream PascalFrancis, to step Checkpoint: 000699
- to stream Main, to step Merge: 007F58
- to stream Main, to step Curation: 007A54
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Frequency and Wavelet Filtering for Robust Speech Recognition</title>
<author><name sortKey="Deviren, Murat" sort="Deviren, Murat" uniqKey="Deviren M" first="Murat" last="Deviren">Murat Deviren</name>
</author>
<author><name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:8FE4D20BDF033D699283D21767C34AC9DC96783C</idno>
<date when="2003" year="2003">2003</date>
<idno type="doi">10.1007/3-540-44989-2_54</idno>
<idno type="url">https://api.istex.fr/ark:/67375/HCB-71GSMGP7-4/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002149</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002149</idno>
<idno type="wicri:Area/Istex/Curation">002121</idno>
<idno type="wicri:Area/Istex/Checkpoint">001A44</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001A44</idno>
<idno type="wicri:doubleKey">0302-9743:2003:Deviren M:frequency:and:wavelet</idno>
<idno type="wicri:Area/Main/Merge">007E33</idno>
<idno type="wicri:source">INIST</idno>
<idno type="RBID">Pascal:04-0130632</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000727</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000314</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000699</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000699</idno>
<idno type="wicri:doubleKey">0302-9743:2003:Deviren M:frequency:and:wavelet</idno>
<idno type="wicri:Area/Main/Merge">007F58</idno>
<idno type="wicri:Area/Main/Curation">007A54</idno>
<idno type="wicri:Area/Main/Exploration">007A54</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Frequency and Wavelet Filtering for Robust Speech Recognition</title>
<author><name sortKey="Deviren, Murat" sort="Deviren, Murat" uniqKey="Deviren M" first="Murat" last="Deviren">Murat Deviren</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>INRIA-LORIA (Speech Group), B.P. 101, 54602, Villers les Nancy</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Villers les Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
<author><name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>INRIA-LORIA (Speech Group), B.P. 101, 54602, Villers les Nancy</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Villers les Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s" type="main" xml:lang="en">Lecture Notes in Computer Science</title>
<idno type="ISSN">0302-9743</idno>
<idno type="ISSN">0302-9743</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial intelligence</term>
<term>Automatic recognition</term>
<term>Cepstrum</term>
<term>Database</term>
<term>Frequency filtering</term>
<term>Speech recognition</term>
<term>Time response</term>
<term>User interface</term>
<term>Wavelet transformation</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>4372</term>
<term>Base donnée</term>
<term>Cepstre</term>
<term>Filtrage fréquence</term>
<term>Intelligence artificielle</term>
<term>Interface utilisateur</term>
<term>Reconnaissance automatique</term>
<term>Reconnaissance parole</term>
<term>Réponse temporelle</term>
<term>Transformation ondelette</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Base de données</term>
<term>Intelligence artificielle</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Mel-frequency cepstral coefficients (MFCC) are the most widely used features in current speech recognition systems. However, they have a poor physical interpretation and they do not lie in the frequency domain. Frequency filtering (FF) is a technique that has been recently developed to design frequency-localized speech features that perform similar to MFCC in terms of recognition performances. Motivated by our desire to build time-frequency speech models, we wanted to use the FF technique as front-end. However, when evaluating FF on the Aurora-3 database we found some discrepancies in the highly mismatch case. This led us to put FF in another perspective: the wavelet transform. By doing so, we were able to explain the discrepancies and to achieve significant improvements in recognition in the highly mismatch case.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
</country>
<region><li>Grand Est</li>
<li>Lorraine (région)</li>
</region>
<settlement><li>Villers les Nancy</li>
</settlement>
</list>
<tree><country name="France"><region name="Grand Est"><name sortKey="Deviren, Murat" sort="Deviren, Murat" uniqKey="Deviren M" first="Murat" last="Deviren">Murat Deviren</name>
</region>
<name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name>
<name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name>
<name sortKey="Deviren, Murat" sort="Deviren, Murat" uniqKey="Deviren M" first="Murat" last="Deviren">Murat Deviren</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 007A54 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 007A54 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:8FE4D20BDF033D699283D21767C34AC9DC96783C |texte= Frequency and Wavelet Filtering for Robust Speech Recognition }}
This area was generated with Dilib version V0.6.33. |