Acoustic-Phonetic Decoding : An Important Issue in Continuous Speech Recognition
Identifieur interne : 00D360 ( Main/Exploration ); précédent : 00D359; suivant : 00D361Acoustic-Phonetic Decoding : An Important Issue in Continuous Speech Recognition
Auteurs : Jean-Paul Haton [France]Source :
English descriptors
Abstract
The acoustic-phonetic decoding of speech (i.e. the transformation of the acoustic continuum of the speech signal into a description under the form of discrete, linguistic units) constitutes an important step and a major bottleneck in the process of automatic speech recognition. This paper presents the problem and its difficulties together with the different families of solutions proposed so far. After a recall of the methods based on pattern matching techniques and stochastic models we introduce a class of methods based on artificial intelligence knowledge-based techniques. Such methods make an explicit use of all available types of knowledge that intervene in speech perception. We then present the use of neural connectionist models and discuss their interest for the problem. The presentation will be illustrated by practical examples drawn from different systems.
Affiliations:
- France
- Grand Est, Lorraine (région)
- Nancy
- Centre national de la recherche scientifique, Institut national de recherche en informatique et en automatique, Laboratoire lorrain de recherche en informatique et ses applications, Université de Lorraine
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 000F44
- to stream Crin, to step Curation: 000F44
- to stream Crin, to step Checkpoint: 003617
- to stream Main, to step Merge: 00DC37
- to stream Main, to step Curation: 00D360
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="593">Acoustic-Phonetic Decoding : An Important Issue in Continuous Speech Recognition</title></titleStmt><publicationStmt><idno type="RBID">CRIN:haton92g</idno><date when="1992" year="1992">1992</date><idno type="wicri:Area/Crin/Corpus">000F44</idno><idno type="wicri:Area/Crin/Curation">000F44</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000F44</idno><idno type="wicri:Area/Crin/Checkpoint">003617</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003617</idno><idno type="wicri:Area/Main/Merge">00DC37</idno><idno type="wicri:Area/Main/Curation">00D360</idno><idno type="wicri:Area/Main/Exploration">00D360</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Acoustic-Phonetic Decoding : An Important Issue in Continuous Speech Recognition</title><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>acoustic-phonetic decoding</term><term>speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2210">The acoustic-phonetic decoding of speech (i.e. the transformation of the acoustic continuum of the speech signal into a description under the form of discrete, linguistic units) constitutes an important step and a major bottleneck in the process of automatic speech recognition. This paper presents the problem and its difficulties together with the different families of solutions proposed so far. After a recall of the methods based on pattern matching techniques and stochastic models we introduce a class of methods based on artificial intelligence knowledge-based techniques. Such methods make an explicit use of all available types of knowledge that intervene in speech perception. We then present the use of neural connectionist models and discuss their interest for the problem. The presentation will be illustrated by practical examples drawn from different systems.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Nancy</li></settlement><orgName><li>Centre national de la recherche scientifique</li><li>Institut national de recherche en informatique et en automatique</li><li>Laboratoire lorrain de recherche en informatique et ses applications</li><li>Université de Lorraine</li></orgName></list><tree><country name="France"><region name="Grand Est"><name sortKey="Haton, J P" sort="Haton, J P" uniqKey="Haton J" first="J.-P." last="Haton">Jean-Paul Haton</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 00D360 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00D360 | 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= CRIN:haton92g
|texte= Acoustic-Phonetic Decoding : An Important Issue in Continuous Speech Recognition
}}
| This area was generated with Dilib version V0.6.33. |  |