Discriminative and Selectively Trained Neural Networks as Static Classifiers for Automatic Speech Recognition
Identifieur interne : 00CC06 ( Main/Merge ); précédent : 00CC05; suivant : 00CC07Discriminative and Selectively Trained Neural Networks as Static Classifiers for Automatic Speech Recognition
Auteurs : J.-C. Junqua ; D. Fohr ; Y. AngladeSource :
English descriptors
Abstract
After a brief overview of the use and the advantages of Artificial Neural Networks (ANNs) in Automatic Speech recognition (ASR), we summarize the main categories of neural network-based hybrid systems. Then, we describe a discriminant method based on Selectively Trained Neural Networks (STNNs) and present its application to four different kinds of problems. We conclude this paper by summarizing the benefits of STNN in these applications which result from research carried out at both the CRIN/INRIA laboratory in France and Speech Technology Laboratory, Santa Barbara.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001A33
- to stream Crin, to step Curation: 001A33
- to stream Crin, to step Checkpoint: 002B61
Links to Exploration step
CRIN:junqua95dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="458">Discriminative and Selectively Trained Neural Networks as Static Classifiers for Automatic Speech Recognition</title></titleStmt><publicationStmt><idno type="RBID">CRIN:junqua95d</idno><date when="1995" year="1995">1995</date><idno type="wicri:Area/Crin/Corpus">001A33</idno><idno type="wicri:Area/Crin/Curation">001A33</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001A33</idno><idno type="wicri:Area/Crin/Checkpoint">002B61</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002B61</idno><idno type="wicri:Area/Main/Merge">00CC06</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Discriminative and Selectively Trained Neural Networks as Static Classifiers for Automatic Speech Recognition</title><author><name sortKey="Junqua, J C" sort="Junqua, J C" uniqKey="Junqua J" first="J.-C." last="Junqua">J.-C. Junqua</name></author><author><name sortKey="Fohr, D" sort="Fohr, D" uniqKey="Fohr D" first="D." last="Fohr">D. Fohr</name></author><author><name sortKey="Anglade, Y" sort="Anglade, Y" uniqKey="Anglade Y" first="Y." last="Anglade">Y. Anglade</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>automatic speech recognition</term><term>neural network</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="1309">After a brief overview of the use and the advantages of Artificial Neural Networks (ANNs) in Automatic Speech recognition (ASR), we summarize the main categories of neural network-based hybrid systems. Then, we describe a discriminant method based on Selectively Trained Neural Networks (STNNs) and present its application to four different kinds of problems. We conclude this paper by summarizing the benefits of STNN in these applications which result from research carried out at both the CRIN/INRIA laboratory in France and Speech Technology Laboratory, Santa Barbara.</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 00CC06 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00CC06 | 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:junqua95d
|texte= Discriminative and Selectively Trained Neural Networks as Static Classifiers for Automatic Speech Recognition
}}
| This area was generated with Dilib version V0.6.33. |  |