On the comparison of front-ends for robust speech recognition in car environments
Identifieur interne : 009429 ( Main/Merge ); précédent : 009428; suivant : 009430On the comparison of front-ends for robust speech recognition in car environments
Auteurs : Angel De La Torre ; Dominique Fohr ; Jean-Paul Haton [France]Source :
English descriptors
- KwdEn :
Abstract
In this paper we compare several front-ends for Automatic Speech Recognition systems operating under noise conditions. The analyzed front-ends are based on standard MFCC parameterizations and include methods to compensate the effect of the noise over the representation of the speech signal. Three different compensation methods are considered in this work : Cepstral Mean Normalization, Spectral Subtraction and a novel method that we propose, based on a Statistical Compensation of the noise in the logarithmic Filter Bank Output domain. The considered front-ends are evaluated with Automatic Speech Recognition experiments using speech acquired in car environments. Making use of the French VODIS speech database (recorded in several cars running in real traffic situations) we have carried out recognition experiments to compare the different front-ends. The results show that the front-end including the Statistical Compensation of the noise outperforms the other considered methods.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003037
- to stream Crin, to step Curation: 003037
- to stream Crin, to step Checkpoint: 001524
Links to Exploration step
CRIN:de_la_torre01aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="482">On the comparison of front-ends for robust speech recognition in car environments</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:de_la_torre01a</idno>
<date when="2001" year="2001">2001</date>
<idno type="wicri:Area/Crin/Corpus">003037</idno>
<idno type="wicri:Area/Crin/Curation">003037</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003037</idno>
<idno type="wicri:Area/Crin/Checkpoint">001524</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">001524</idno>
<idno type="wicri:Area/Main/Merge">009429</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">On the comparison of front-ends for robust speech recognition in car environments</title>
<author><name sortKey="De La Torre, Angel" sort="De La Torre, Angel" uniqKey="De La Torre A" first="Angel" last="De La Torre">Angel De La Torre</name>
</author>
<author><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name>
</author>
<author><name sortKey="Haton, Jean Paul" sort="Haton, Jean Paul" uniqKey="Haton J" first="Jean-Paul" last="Haton">Jean-Paul Haton</name>
<affiliation><country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>adaptation</term>
<term>noise compensation</term>
<term>speech recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3068">In this paper we compare several front-ends for Automatic Speech Recognition systems operating under noise conditions. The analyzed front-ends are based on standard MFCC parameterizations and include methods to compensate the effect of the noise over the representation of the speech signal. Three different compensation methods are considered in this work : Cepstral Mean Normalization, Spectral Subtraction and a novel method that we propose, based on a Statistical Compensation of the noise in the logarithmic Filter Bank Output domain. The considered front-ends are evaluated with Automatic Speech Recognition experiments using speech acquired in car environments. Making use of the French VODIS speech database (recorded in several cars running in real traffic situations) we have carried out recognition experiments to compare the different front-ends. The results show that the front-end including the Statistical Compensation of the noise outperforms the other considered methods.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 009429 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 009429 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Merge |type= RBID |clé= CRIN:de_la_torre01a |texte= On the comparison of front-ends for robust speech recognition in car environments }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |