The automatic speech recognition engine ESPERE : experiments on telephone speech
Identifieur interne : 001A15 ( Crin/Checkpoint ); précédent : 001A14; suivant : 001A16The automatic speech recognition engine ESPERE : experiments on telephone speech
Auteurs : Dominique Fohr ; Odile Mella ; Christophe AntoineSource :
English descriptors
- KwdEn :
Abstract
This paper presents our automatic speech recognition engine ESPERE and several results obtained from experiments on telephone speech. ESPERE (Engine for SPEech REcognition) is a HMM-based toolbox for speech recognition allowing the user to choose the modeled unit (word, phone, triphone), define the topology of every Hidden Markov Model, train the models with the Baum-Welch algorithm and evaluate the recognition accuracy on speech databases. To validate the ESPERE toolbox, we have conducted tests on real world data : the recognition of a three-digit code to access a call center. We have investigated the influence of some parameters and some preprocessing algorithms. Finally, combining the best parameters, the recognition score reaches 96.4% at the word level and 92.1% at the sentence level.
Links toward previous steps (curation, corpus...)
Links to Exploration step
CRIN:fohr00aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="361">The automatic speech recognition engine ESPERE : experiments on telephone speech</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:fohr00a</idno>
<date when="2000" year="2000">2000</date>
<idno type="wicri:Area/Crin/Corpus">002B48</idno>
<idno type="wicri:Area/Crin/Curation">002B48</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">002B48</idno>
<idno type="wicri:Area/Crin/Checkpoint">001A15</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">001A15</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">The automatic speech recognition engine ESPERE : experiments on telephone speech</title>
<author><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name>
</author>
<author><name sortKey="Mella, Odile" sort="Mella, Odile" uniqKey="Mella O" first="Odile" last="Mella">Odile Mella</name>
</author>
<author><name sortKey="Antoine, Christophe" sort="Antoine, Christophe" uniqKey="Antoine C" first="Christophe" last="Antoine">Christophe Antoine</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>hmm</term>
<term>speech recognition</term>
<term>telephone speech</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="2405">This paper presents our automatic speech recognition engine ESPERE and several results obtained from experiments on telephone speech. ESPERE (Engine for SPEech REcognition) is a HMM-based toolbox for speech recognition allowing the user to choose the modeled unit (word, phone, triphone), define the topology of every Hidden Markov Model, train the models with the Baum-Welch algorithm and evaluate the recognition accuracy on speech databases. To validate the ESPERE toolbox, we have conducted tests on real world data : the recognition of a three-digit code to access a call center. We have investigated the influence of some parameters and some preprocessing algorithms. Finally, combining the best parameters, the recognition score reaches 96.4% at the word level and 92.1% at the sentence level.</div>
</front>
</TEI>
<BibTex type="inproceedings"><ref>fohr00a</ref>
<crinnumber>A00-R-257</crinnumber>
<category>3</category>
<equipe>PAROLE</equipe>
<author><e>Fohr, Dominique</e>
<e>Mella, Odile</e>
<e>Antoine, Christophe</e>
</author>
<title>The automatic speech recognition engine ESPERE : experiments on telephone speech</title>
<booktitle>{ICSLP, Pékin, China}</booktitle>
<year>2000</year>
<month>Oct</month>
<keywords><e>speech recognition</e>
<e>hmm</e>
<e>telephone speech</e>
</keywords>
<abstract>This paper presents our automatic speech recognition engine ESPERE and several results obtained from experiments on telephone speech. ESPERE (Engine for SPEech REcognition) is a HMM-based toolbox for speech recognition allowing the user to choose the modeled unit (word, phone, triphone), define the topology of every Hidden Markov Model, train the models with the Baum-Welch algorithm and evaluate the recognition accuracy on speech databases. To validate the ESPERE toolbox, we have conducted tests on real world data : the recognition of a three-digit code to access a call center. We have investigated the influence of some parameters and some preprocessing algorithms. Finally, combining the best parameters, the recognition score reaches 96.4% at the word level and 92.1% at the sentence level.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001A15 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Checkpoint/biblio.hfd -nk 001A15 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Checkpoint |type= RBID |clé= CRIN:fohr00a |texte= The automatic speech recognition engine ESPERE : experiments on telephone speech }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |