A Knowledge based Approach for Automatic Labeling of a Large Speech Database
Identifieur interne : 00E818 ( Main/Merge ); précédent : 00E817; suivant : 00E819A Knowledge based Approach for Automatic Labeling of a Large Speech Database
Auteurs : J.-C. Junqua ; H. WakitaSource :
English descriptors
- KwdEn :
Abstract
SAIPH is an automatic labeling system which does not require reference units and takes advantage of a modular architecture. Thus it can be applied to automatic labeling of a speech database as well as to automatic speech recognition. In this paper we present the segmentation method followed by evaluation results. Then we focus on alternate knowledge sources applied for further improvement.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 000803
- to stream Crin, to step Curation: 000803
- to stream Crin, to step Checkpoint: 003D66
Links to Exploration step
CRIN:junqua89dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="345">A Knowledge based Approach for Automatic Labeling of a Large Speech Database</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:junqua89d</idno>
<date when="1989" year="1989">1989</date>
<idno type="wicri:Area/Crin/Corpus">000803</idno>
<idno type="wicri:Area/Crin/Curation">000803</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000803</idno>
<idno type="wicri:Area/Crin/Checkpoint">003D66</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003D66</idno>
<idno type="wicri:Area/Main/Merge">00E818</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">A Knowledge based Approach for Automatic Labeling of a Large Speech Database</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="Wakita, H" sort="Wakita, H" uniqKey="Wakita H" first="H." last="Wakita">H. Wakita</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>blackboard</term>
<term>knowledge sources</term>
<term>labeling</term>
<term>segmentation</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1055">SAIPH is an automatic labeling system which does not require reference units and takes advantage of a modular architecture. Thus it can be applied to automatic labeling of a speech database as well as to automatic speech recognition. In this paper we present the segmentation method followed by evaluation results. Then we focus on alternate knowledge sources applied for further improvement.</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 00E818 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00E818 | 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:junqua89d |texte= A Knowledge based Approach for Automatic Labeling of a Large Speech Database }}
This area was generated with Dilib version V0.6.33. |