Stochastic Trajectory Models for Speech Recognition : An Extension to Modelling Time Correlation
Identifieur interne : 00CB49 ( Main/Merge ); précédent : 00CB48; suivant : 00CB50Stochastic Trajectory Models for Speech Recognition : An Extension to Modelling Time Correlation
Auteurs : M. Afify ; Y. Gong ; Jean-Paul Haton [France]Source :
English descriptors
- KwdEn :
Abstract
Based on experimental evidence from other research work, we assume that speech signals in consecutive analysis frames are correlated and we explore the correlation for speech recognition in the framework of stochastic trajectory models (STM). In this paper, we extend our previously proposed stochastic mixture trajectory models to model such a time correlation. Specifically, we consider the observation sequence of a speech signal as being generated by a mixture of random trajectory generators, and explicitly model the time evolution of the mean vector of each trajectory as the sum of a first order non-observable AR process and a state dependent random process. We describe the main results of the formulation, parameter estimation and sentence recognition. Evaluated on a speaker-dependent continuous speech recognition task, the proposed approach reduced average word error rate by about 25========percnt;, compared to a baseline STM system in which frames are assumed to be independent.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001A26
- to stream Crin, to step Curation: 001A26
- to stream Crin, to step Checkpoint: 002B04
Links to Exploration step
CRIN:afify95aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="644">Stochastic Trajectory Models for Speech Recognition : An Extension to Modelling Time Correlation</title></titleStmt><publicationStmt><idno type="RBID">CRIN:afify95a</idno><date when="1995" year="1995">1995</date><idno type="wicri:Area/Crin/Corpus">001A26</idno><idno type="wicri:Area/Crin/Curation">001A26</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001A26</idno><idno type="wicri:Area/Crin/Checkpoint">002B04</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002B04</idno><idno type="wicri:Area/Main/Merge">00CB49</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Stochastic Trajectory Models for Speech Recognition : An Extension to Modelling Time Correlation</title><author><name sortKey="Afify, M" sort="Afify, M" uniqKey="Afify M" first="M." last="Afify">M. Afify</name></author><author><name sortKey="Gong, Y" sort="Gong, Y" uniqKey="Gong Y" first="Y." last="Gong">Y. Gong</name></author><author><name sortKey="Haton, J P" sort="Haton, J P" uniqKey="Haton J" first="J.-P." last="Haton">Jean-Paul Haton</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>speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="1631">Based on experimental evidence from other research work, we assume that speech signals in consecutive analysis frames are correlated and we explore the correlation for speech recognition in the framework of stochastic trajectory models (STM). In this paper, we extend our previously proposed stochastic mixture trajectory models to model such a time correlation. Specifically, we consider the observation sequence of a speech signal as being generated by a mixture of random trajectory generators, and explicitly model the time evolution of the mean vector of each trajectory as the sum of a first order non-observable AR process and a state dependent random process. We describe the main results of the formulation, parameter estimation and sentence recognition. Evaluated on a speaker-dependent continuous speech recognition task, the proposed approach reduced average word error rate by about 25========percnt;, compared to a baseline STM system in which frames are assumed to be independent.</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 00CB49 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00CB49 | 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:afify95a
|texte= Stochastic Trajectory Models for Speech Recognition : An Extension to Modelling Time Correlation
}}
| This area was generated with Dilib version V0.6.33. |  |