Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition
Identifieur interne : 003742 ( Crin/Curation ); précédent : 003741; suivant : 003743Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition
Auteurs : Khalid Daoudi ; Dominique Fohr ; Christophe AntoineSource :
- Computer Speech and Language ; 2003.
English descriptors
- KwdEn :
Abstract
This paper presents a new approach to multi-band automatic speech recognition which has the advantage to overcome many limitations of classical muti-band systems. The principle of this new approach is to build a speech model in the time-frequency domain using the formalism of dynamic Bayesian networks. In contrast to classical multi-band modeling, this formalism leads to a probabilistic speech model which allows communications between the different sub-bands and, consequently, no recombination step is required in recognition. We develop efficient learning and decoding algorithms both for isolated and continuous speech recognition. We present illustrative experiments on isolated and connected digit recognition tasks. These experiments show that the this new approach is very promising in the field of noisy speech recognition.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :003742
Links to Exploration step
CRIN:daoudi02bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="490">Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:daoudi02b</idno>
<date when="2003" year="2003">2003</date>
<idno type="wicri:Area/Crin/Corpus">003742</idno>
<idno type="wicri:Area/Crin/Curation">003742</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003742</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition</title>
<author><name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name>
</author>
<author><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name>
</author>
<author><name sortKey="Antoine, Christophe" sort="Antoine, Christophe" uniqKey="Antoine C" first="Christophe" last="Antoine">Christophe Antoine</name>
</author>
</analytic>
<series><title level="j">Computer Speech and Language</title>
<imprint><date when="2003" type="published">2003</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>bayesian networks</term>
<term>speech recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3647">This paper presents a new approach to multi-band automatic speech recognition which has the advantage to overcome many limitations of classical muti-band systems. The principle of this new approach is to build a speech model in the time-frequency domain using the formalism of dynamic Bayesian networks. In contrast to classical multi-band modeling, this formalism leads to a probabilistic speech model which allows communications between the different sub-bands and, consequently, no recombination step is required in recognition. We develop efficient learning and decoding algorithms both for isolated and continuous speech recognition. We present illustrative experiments on isolated and connected digit recognition tasks. These experiments show that the this new approach is very promising in the field of noisy speech recognition.</div>
</front>
</TEI>
<BibTex type="article"><ref>daoudi02b</ref>
<crinnumber>A02-R-278</crinnumber>
<category>1</category>
<equipe>PAROLE</equipe>
<author><e>Daoudi, Khalid</e>
<e>Fohr, Dominique</e>
<e>Antoine, Christophe</e>
</author>
<title>Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition</title>
<journal>Computer Speech and Language</journal>
<year>2003</year>
<volume>17</volume>
<number>2-3</number>
<pages>263-285</pages>
<month>Jul</month>
<keywords><e>speech recognition</e>
<e>bayesian networks</e>
</keywords>
<abstract>This paper presents a new approach to multi-band automatic speech recognition which has the advantage to overcome many limitations of classical muti-band systems. The principle of this new approach is to build a speech model in the time-frequency domain using the formalism of dynamic Bayesian networks. In contrast to classical multi-band modeling, this formalism leads to a probabilistic speech model which allows communications between the different sub-bands and, consequently, no recombination step is required in recognition. We develop efficient learning and decoding algorithms both for isolated and continuous speech recognition. We present illustrative experiments on isolated and connected digit recognition tasks. These experiments show that the this new approach is very promising in the field of noisy speech recognition.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003742 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Curation/biblio.hfd -nk 003742 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Curation |type= RBID |clé= CRIN:daoudi02b |texte= Dynamic Bayesian Networks for Multi-Band Automatic Speech Recognition }}
This area was generated with Dilib version V0.6.33. |