Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm
Identifieur interne : 008752 ( Main/Merge ); précédent : 008751; suivant : 008753Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm
Auteurs : Murat Deviren ; Khalid DaoudiSource :
English descriptors
Abstract
State-of-the-art automatic speech recognition systems are based on probabilistic modelling 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
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003407
- to stream Crin, to step Curation: 003407
- to stream Crin, to step Checkpoint: 000F84
Links to Exploration step
CRIN:deviren02dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="661">Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm</title></titleStmt><publicationStmt><idno type="RBID">CRIN:deviren02d</idno><date when="2002" year="2002">2002</date><idno type="wicri:Area/Crin/Corpus">003407</idno><idno type="wicri:Area/Crin/Curation">003407</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003407</idno><idno type="wicri:Area/Crin/Checkpoint">000F84</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000F84</idno><idno type="wicri:Area/Main/Merge">008752</idno></publicationStmt><sourceDesc><biblStruct><analytic><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></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>dynamic bayesian networks</term><term>speech decoding</term><term>speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="3118">State-of-the-art automatic speech recognition systems are based on probabilistic modelling 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/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 008752 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 008752 | 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:deviren02d
|texte= Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm
}}
| This area was generated with Dilib version V0.6.33. |  |