Continuous Speech Recognition Using Dynamic Bayesian Networks: A Fast Decoding Algorithm
Identifieur interne : 006C23 ( Main/Curation ); précédent : 006C22; suivant : 006C24Continuous Speech Recognition Using Dynamic Bayesian Networks: A Fast Decoding Algorithm
Auteurs : Murat Deviren [France] ; Khalid Daoudi [France]Source :
- Studies in Fuzziness and Soft Computing [ 1434-9922 ]
Abstract
Abstract: State-of-the-art automatic speech recognition systems are based on probabilistic modeling of the speech signal using Hidden Markov Models (HMMs). Recent work has focused on the use of dynamic Bayesian networks (DBNs) framework to construct new acoustic models to overcome the limitations of HMM based systems. In this line of research we proposed a methodology to learn the conditional independence assertions of acoustic models based on structural learning of DBNs. In previous work, we evaluated this approach for simple isolated and connected digit recognition tasks. In this paper we evaluate our approach for a more complex task: continuous phoneme recognition. For this purpose, we propose a new decoding algorithm based on dynamic programming. The proposed algorithm decreases the computational complexity of decoding and hence enables the application of the approach to complex speech recognition tasks.
Url:
DOI: 10.1007/978-3-540-39879-0_16
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :003013
- to stream Istex, to step Curation: Pour aller vers cette notice dans l'étape Curation :002F74
- to stream Istex, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :001832
- to stream Main, to step Merge: Pour aller vers cette notice dans l'étape Curation :006F27
Links to Exploration step
ISTEX:CAECBF3D332D0BEC13E478C9A063976DF7DCCF7CLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Continuous Speech Recognition Using Dynamic Bayesian Networks: A Fast Decoding Algorithm</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:CAECBF3D332D0BEC13E478C9A063976DF7DCCF7C</idno>
<date when="2004" year="2004">2004</date>
<idno type="doi">10.1007/978-3-540-39879-0_16</idno>
<idno type="url">https://api.istex.fr/ark:/67375/HCB-X8H70WTR-P/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">003013</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">003013</idno>
<idno type="wicri:Area/Istex/Curation">002F74</idno>
<idno type="wicri:Area/Istex/Checkpoint">001832</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001832</idno>
<idno type="wicri:doubleKey">1434-9922:2004:Deviren M:continuous:speech:recognition</idno>
<idno type="wicri:Area/Main/Merge">006F27</idno>
<idno type="wicri:Area/Main/Curation">006C23</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Continuous Speech Recognition Using Dynamic Bayesian Networks: A Fast Decoding Algorithm</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 lès 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 lès Nancy</settlement>
</placeName>
</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 lès 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 lès Nancy</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s" type="main" xml:lang="en">Studies in Fuzziness and Soft Computing</title>
<idno type="ISSN">1434-9922</idno>
<idno type="eISSN">1860-0808</idno>
<idno type="ISSN">1434-9922</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">1434-9922</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: State-of-the-art automatic speech recognition systems are based on probabilistic modeling of the speech signal using Hidden Markov Models (HMMs). Recent work has focused on the use of dynamic Bayesian networks (DBNs) framework to construct new acoustic models to overcome the limitations of HMM based systems. In this line of research we proposed a methodology to learn the conditional independence assertions of acoustic models based on structural learning of DBNs. In previous work, we evaluated this approach for simple isolated and connected digit recognition tasks. In this paper we evaluate our approach for a more complex task: continuous phoneme recognition. For this purpose, we propose a new decoding algorithm based on dynamic programming. The proposed algorithm decreases the computational complexity of decoding and hence enables the application of the approach to complex speech recognition tasks.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 006C23 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Curation/biblio.hfd -nk 006C23 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Curation |type= RBID |clé= ISTEX:CAECBF3D332D0BEC13E478C9A063976DF7DCCF7C |texte= Continuous Speech Recognition Using Dynamic Bayesian Networks: A Fast Decoding Algorithm }}
This area was generated with Dilib version V0.6.33. |