Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole
Identifieur interne : 008228 ( Main/Exploration ); précédent : 008227; suivant : 008229Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole
Auteurs : Khalid Daoudi ; Dominique Fohr ; Christophe AntoineSource :
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 Bayesian networks. Contrarily 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 and present illustrative experiments on a connected digit recognition task. The experiments show that the Bayesian network's approach is very promising in the field of noisy speech recognition.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003453
- to stream Crin, to step Curation: 003453
- to stream Crin, to step Checkpoint: 000F43
- to stream Main, to step Merge: 008704
- to stream Main, to step Curation: 008228
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="fr" wicri:score="-106">Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole</title></titleStmt><publicationStmt><idno type="RBID">CRIN:daoudi02d</idno><date when="2002" year="2002">2002</date><idno type="wicri:Area/Crin/Corpus">003453</idno><idno type="wicri:Area/Crin/Curation">003453</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003453</idno><idno type="wicri:Area/Crin/Checkpoint">000F43</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000F43</idno><idno type="wicri:Area/Main/Merge">008704</idno><idno type="wicri:Area/Main/Curation">008228</idno><idno type="wicri:Area/Main/Exploration">008228</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="fr">Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole</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></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="3267">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 Bayesian networks. Contrarily 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 and present illustrative experiments on a connected digit recognition task. The experiments show that the Bayesian network's approach is very promising in the field of noisy speech recognition.</div></front></TEI><affiliations><list></list><tree><noCountry><name sortKey="Antoine, Christophe" sort="Antoine, Christophe" uniqKey="Antoine C" first="Christophe" last="Antoine">Christophe Antoine</name><name sortKey="Daoudi, Khalid" sort="Daoudi, Khalid" uniqKey="Daoudi K" first="Khalid" last="Daoudi">Khalid Daoudi</name><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name></noCountry></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 008228 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 008228 | 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= CRIN:daoudi02d
|texte= Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole
}}
| This area was generated with Dilib version V0.6.33. |  |