Plausibility Functions in Continuous Speech Recognition : {The} {VINICS} System
Identifieur interne : 00D802 ( Main/Merge ); précédent : 00D801; suivant : 00D803Plausibility Functions in Continuous Speech Recognition : {The} {VINICS} System
Auteurs : Y. Gong ; Jean-Paul Haton [France]Source :
- Speech Communication ; 1993.
English descriptors
Abstract
We propose a new approach to phoneme-based continuous speech recognition when a time function of plausibility of observing each phoneme is given. We introduce a criterion for best sentence, related to the sum of plausibilities of individual symbols composing the sentence. Based on the idea of making use of a high plausibility region to reduce the computation load while keeping optimality, our method finds the most plausible sentences relating to the input speech, given the plausibility \mua,n of observing each phoneme a at each time slot n. Two optimization procedures are defined to deal with the following embedded search processes\, : (1) find the best path connecting peaks of the plausibility functions of two successive symbols, and (2) find the best time transition slot index for two given peaks. Dynamic programming is used in these two procedures. Since the best path finding algorithm does not search slot by slot, the recognition is highly efficient. Experimental results with the VINICS system show that the method gives a better recognition precision while requiring about 1/20 computing time, compared to traditional DP based methods. The experimental system obtained a 95========percnt; sentence recognition rate on a speaker-dependent test.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001225
- to stream Crin, to step Curation: 001225
- to stream Crin, to step Checkpoint: 003330
Links to Exploration step
CRIN:gong93dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="519">Plausibility Functions in Continuous Speech Recognition : {The} {VINICS} System</title></titleStmt><publicationStmt><idno type="RBID">CRIN:gong93d</idno><date when="1993" year="1993">1993</date><idno type="wicri:Area/Crin/Corpus">001225</idno><idno type="wicri:Area/Crin/Curation">001225</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001225</idno><idno type="wicri:Area/Crin/Checkpoint">003330</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003330</idno><idno type="wicri:Area/Main/Merge">00D802</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Plausibility Functions in Continuous Speech Recognition : {The} {VINICS} System</title><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><series><title level="j">Speech Communication</title><imprint><date when="1993" type="published">1993</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>neural networks</term><term>phoneme recognition</term><term>speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="4626">We propose a new approach to phoneme-based continuous speech recognition when a time function of plausibility of observing each phoneme is given. We introduce a criterion for best sentence, related to the sum of plausibilities of individual symbols composing the sentence. Based on the idea of making use of a high plausibility region to reduce the computation load while keeping optimality, our method finds the most plausible sentences relating to the input speech, given the plausibility \mua,n of observing each phoneme a at each time slot n. Two optimization procedures are defined to deal with the following embedded search processes\, : (1) find the best path connecting peaks of the plausibility functions of two successive symbols, and (2) find the best time transition slot index for two given peaks. Dynamic programming is used in these two procedures. Since the best path finding algorithm does not search slot by slot, the recognition is highly efficient. Experimental results with the VINICS system show that the method gives a better recognition precision while requiring about 1/20 computing time, compared to traditional DP based methods. The experimental system obtained a 95========percnt; sentence recognition rate on a speaker-dependent test.</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 00D802 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00D802 | 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:gong93d
|texte= Plausibility Functions in Continuous Speech Recognition : {The} {VINICS} System
}}
| This area was generated with Dilib version V0.6.33. |  |