Recognition and Rejection Performance in Wordspotting Systems Using Hidden Markov modeling techniques
Identifieur interne : 008331 ( Main/Exploration ); précédent : 008330; suivant : 008332Recognition and Rejection Performance in Wordspotting Systems Using Hidden Markov modeling techniques
Auteurs : Yassine Benayed ; Dominique Fohr ; Jean-Paul Haton [France] ; Gérard CholletSource :
English descriptors
- KwdEn :
Abstract
This paper deals with the problem of acceptance/rejection of recognition hypotheses for continuous speech utterances. Two different techniques are investigated to improve the rejection of out-of-vocabulary (OOV) words. A combined approach is first proposed which uses two garbage models (a trained one and an on-line garbage model). The second method uses the trained garbage model and consists in post-processing the recognizer hypotheses by computing for each of them a confidence measure. Both approaches are evaluated in the context of a stock exchange application through the telephone for French. The parameters of the two approaches are studied to improve recognition accuracy.
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: 003382
- to stream Crin, to step Curation: 003382
- to stream Crin, to step Checkpoint: 001019
- to stream Main, to step Merge: 008787
- to stream Main, to step Curation: 008331
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="543">Recognition and Rejection Performance in Wordspotting Systems Using Hidden Markov modeling techniques</title></titleStmt><publicationStmt><idno type="RBID">CRIN:benayed02c</idno><date when="2002" year="2002">2002</date><idno type="wicri:Area/Crin/Corpus">003382</idno><idno type="wicri:Area/Crin/Curation">003382</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003382</idno><idno type="wicri:Area/Crin/Checkpoint">001019</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">001019</idno><idno type="wicri:Area/Main/Merge">008787</idno><idno type="wicri:Area/Main/Curation">008331</idno><idno type="wicri:Area/Main/Exploration">008331</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Recognition and Rejection Performance in Wordspotting Systems Using Hidden Markov modeling techniques</title><author><name sortKey="Benayed, Yassine" sort="Benayed, Yassine" uniqKey="Benayed Y" first="Yassine" last="Benayed">Yassine Benayed</name></author><author><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name></author><author><name sortKey="Haton, Jean Paul" sort="Haton, Jean Paul" uniqKey="Haton J" first="Jean-Paul" 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><author><name sortKey="Chollet, Gerard" sort="Chollet, Gerard" uniqKey="Chollet G" first="Gérard" last="Chollet">Gérard Chollet</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>hidden markov models</term><term>keywords</term><term>spotting</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="1816">This paper deals with the problem of acceptance/rejection of recognition hypotheses for continuous speech utterances. Two different techniques are investigated to improve the rejection of out-of-vocabulary (OOV) words. A combined approach is first proposed which uses two garbage models (a trained one and an on-line garbage model). The second method uses the trained garbage model and consists in post-processing the recognizer hypotheses by computing for each of them a confidence measure. Both approaches are evaluated in the context of a stock exchange application through the telephone for French. The parameters of the two approaches are studied to improve recognition accuracy.</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><noCountry><name sortKey="Benayed, Yassine" sort="Benayed, Yassine" uniqKey="Benayed Y" first="Yassine" last="Benayed">Yassine Benayed</name><name sortKey="Chollet, Gerard" sort="Chollet, Gerard" uniqKey="Chollet G" first="Gérard" last="Chollet">Gérard Chollet</name><name sortKey="Fohr, Dominique" sort="Fohr, Dominique" uniqKey="Fohr D" first="Dominique" last="Fohr">Dominique Fohr</name></noCountry><country name="France"><region name="Grand Est"><name sortKey="Haton, Jean Paul" sort="Haton, Jean Paul" uniqKey="Haton J" first="Jean-Paul" 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 008331 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 008331 | 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:benayed02c
|texte= Recognition and Rejection Performance in Wordspotting Systems Using Hidden Markov modeling techniques
}}
| This area was generated with Dilib version V0.6.33. |  |