Fréquence fondamentale et durée pour la détection de frontières syntagmatiques en parole continue
Identifieur interne : 00E405 ( Main/Merge ); précédent : 00E404; suivant : 00E406Fréquence fondamentale et durée pour la détection de frontières syntagmatiques en parole continue
Auteurs : J.-J. Bonin ; Jean-Marie Pierrel [France]Source :
English descriptors
- KwdEn :
Abstract
The present communication concerns the use of prosodic parameters in automatic continuous speech recognition and understanding. It is a matter of studying prosodic knowledges and informations for their uses in a natural language task oriented spoken dialogue system (multi-levels knowledge sources system developping in CRIN). Results are discussed concerning the detection of syntagm boundaries from the use of fundamental frequency and rhythm variations. There are presented in a statistical study form which combine FO, vocalic duration and pause cues corresponding to three differents speech production conditions\, : reading, memorized sentences (short-term memory), quasi-spontaneous information dialogues.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 000928
- to stream Crin, to step Curation: 000928
- to stream Crin, to step Checkpoint: 003A70
Links to Exploration step
CRIN:bonin90aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="fr" wicri:score="-68">Fréquence fondamentale et durée pour la détection de frontières syntagmatiques en parole continue</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:bonin90a</idno>
<date when="1990" year="1990">1990</date>
<idno type="wicri:Area/Crin/Corpus">000928</idno>
<idno type="wicri:Area/Crin/Curation">000928</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000928</idno>
<idno type="wicri:Area/Crin/Checkpoint">003A70</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003A70</idno>
<idno type="wicri:Area/Main/Merge">00E405</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="fr">Fréquence fondamentale et durée pour la détection de frontières syntagmatiques en parole continue</title>
<author><name sortKey="Bonin, J J" sort="Bonin, J J" uniqKey="Bonin J" first="J.-J." last="Bonin">J.-J. Bonin</name>
</author>
<author><name sortKey="Pierrel, J M" sort="Pierrel, J M" uniqKey="Pierrel J" first="J.-M." last="Pierrel">Jean-Marie Pierrel</name>
<affiliation><country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>automatic continuous speech recognition/understanding</term>
<term>natural language</term>
<term>prosodic parameters</term>
<term>prosody</term>
<term>spontaneous speech</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1873">The present communication concerns the use of prosodic parameters in automatic continuous speech recognition and understanding. It is a matter of studying prosodic knowledges and informations for their uses in a natural language task oriented spoken dialogue system (multi-levels knowledge sources system developping in CRIN). Results are discussed concerning the detection of syntagm boundaries from the use of fundamental frequency and rhythm variations. There are presented in a statistical study form which combine FO, vocalic duration and pause cues corresponding to three differents speech production conditions\, : reading, memorized sentences (short-term memory), quasi-spontaneous information dialogues.</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 00E405 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00E405 | 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:bonin90a |texte= Fréquence fondamentale et durée pour la détection de frontières syntagmatiques en parole continue }}
This area was generated with Dilib version V0.6.33. |