Short-timed speech dynamics for speaker recognition
Identifieur interne : 00C812 ( Main/Exploration ); précédent : 00C811; suivant : 00C813Short-timed speech dynamics for speaker recognition
Auteurs : H. Li [France] ; J. P. Haton ; J. SuSource :
- Electronics Letters [ 0013-5194 ] ; 1995.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Méthode statistique.
English descriptors
- KwdEn :
- Algorithms, Encoding (symbols), Experiments, Gaussian speaker model, Maximum likelihood estimation, Probability density function, Short-time speech dynamics, Speaker recognition, Speech analysis, Speech coding, Speech processing, Speech recognition, Speech verification, Statistical methods, Temporal transition model, Theory.
Abstract
A temporal transition model of speech is proposed for speaker recognition and verification. The issues of model building, distance measure and implementation are addressed. A set of experiments are conducted, which give a 98.9% recognition rate and 99.5% verification rate. Short-timed dynamics of utterance well encodes the speaker specificity.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000D58
- to stream PascalFrancis, to step Curation: 000B36
- to stream PascalFrancis, to step Checkpoint: 000D24
- to stream Main, to step Merge: 00D073
- to stream Main, to step Curation: 00C812
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Short-timed speech dynamics for speaker recognition</title><author><name sortKey="Li, H" sort="Li, H" uniqKey="Li H" first="H." last="Li">H. Li</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>CRIN-CNRS/INRIA-Lorraine</s1><s2>Vandoeuvre-les-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Vandœuvre-lès-Nancy</settlement><settlement type="city" wicri:auto="agglo">Nancy</settlement></placeName></affiliation></author><author><name sortKey="Haton, J P" sort="Haton, J P" uniqKey="Haton J" first="J. P." last="Haton">J. P. Haton</name></author><author><name sortKey="Su, J" sort="Su, J" uniqKey="Su J" first="J." last="Su">J. Su</name></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">95-0505592</idno><date when="1995">1995</date><idno type="stanalyst">PASCAL 95-0505592 EI</idno><idno type="RBID">Pascal:95-0505592</idno><idno type="wicri:Area/PascalFrancis/Corpus">000D58</idno><idno type="wicri:Area/PascalFrancis/Curation">000B36</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000D24</idno><idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000D24</idno><idno type="wicri:doubleKey">0013-5194:1995:Li H:short:timed:speech</idno><idno type="wicri:Area/Main/Merge">00D073</idno><idno type="wicri:Area/Main/Curation">00C812</idno><idno type="wicri:Area/Main/Exploration">00C812</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Short-timed speech dynamics for speaker recognition</title><author><name sortKey="Li, H" sort="Li, H" uniqKey="Li H" first="H." last="Li">H. Li</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>CRIN-CNRS/INRIA-Lorraine</s1><s2>Vandoeuvre-les-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Vandœuvre-lès-Nancy</settlement><settlement type="city" wicri:auto="agglo">Nancy</settlement></placeName></affiliation></author><author><name sortKey="Haton, J P" sort="Haton, J P" uniqKey="Haton J" first="J. P." last="Haton">J. P. Haton</name></author><author><name sortKey="Su, J" sort="Su, J" uniqKey="Su J" first="J." last="Su">J. Su</name></author></analytic><series><title level="j" type="main">Electronics Letters</title><title level="j" type="abbreviated">Electron Lett</title><idno type="ISSN">0013-5194</idno><imprint><date when="1995">1995</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Electronics Letters</title><title level="j" type="abbreviated">Electron Lett</title><idno type="ISSN">0013-5194</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Encoding (symbols)</term><term>Experiments</term><term>Gaussian speaker model</term><term>Maximum likelihood estimation</term><term>Probability density function</term><term>Short-time speech dynamics</term><term>Speaker recognition</term><term>Speech analysis</term><term>Speech coding</term><term>Speech processing</term><term>Speech recognition</term><term>Speech verification</term><term>Statistical methods</term><term>Temporal transition model</term><term>Theory</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Théorie</term><term>Traitement parole</term><term>Analyse parole</term><term>Codage parole</term><term>Codage symbolique</term><term>Méthode statistique</term><term>Fonction densité probabilité</term><term>Algorithme</term><term>Reconnaissance parole</term><term>Expérience</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Méthode statistique</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">A temporal transition model of speech is proposed for speaker recognition and verification. The issues of model building, distance measure and implementation are addressed. A set of experiments are conducted, which give a 98.9% recognition rate and 99.5% verification rate. Short-timed dynamics of utterance well encodes the speaker specificity.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Nancy</li><li>Vandœuvre-lès-Nancy</li></settlement></list><tree><noCountry><name sortKey="Haton, J P" sort="Haton, J P" uniqKey="Haton J" first="J. P." last="Haton">J. P. Haton</name><name sortKey="Su, J" sort="Su, J" uniqKey="Su J" first="J." last="Su">J. Su</name></noCountry><country name="France"><region name="Grand Est"><name sortKey="Li, H" sort="Li, H" uniqKey="Li H" first="H." last="Li">H. Li</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00C812 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00C812 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:95-0505592
|texte= Short-timed speech dynamics for speaker recognition
}}
| This area was generated with Dilib version V0.6.33. |  |