Local and frame-synchronous confidence measures for automatic speech recognition
Identifieur interne : 002F48 ( Hal/Corpus ); précédent : 002F47; suivant : 002F49Local and frame-synchronous confidence measures for automatic speech recognition
Auteurs : Joseph RazikSource :
Descripteurs français
- mix :
English descriptors
- mix :
Abstract
In automatic speech recognition, confidence measures aim at estimating the confidence we can give to a result (phone, word, sentence) provided by the speech recognition engine; for example, the contribution of the confidence measure allows to highlight the misrecognized or out-of-vocabulary words.
In this thesis, we propose several confidence measures which are able to provide this estimation for applications using large vocabulary and on-the-fly recognition, as keyword indexation, broadcast news transcription, and live teaching class transcription for hard of hearing children.
In this framework, we have defined two types of confidence measures. The first, based on likelihood ratio, are frame-synchronous measures which can be computed simultaneously with the recognition process of the sentence. The second ones are based on an estimation of the posterior probability limited to a local neighborhood of the considered word, and need only a short delay before being computed on the sub word graph extracted from the recognition process.
These measures were assessed and compared to a state-of-the-art one, which is also based on posterior probability but which requires the recognition of the whole sentence. Two evaluations were performed on a real broadcast news corpus provided by the ESTER campaign. The first one used the Equal Error Rate criterion in an automatic transcription task. The second evaluation was performed in a keyword spotting task. We achieved performance close to our reference measure with our local measures and a delay of less than one second.
We also integrated one of our frame-synchronous measures in the decoding process of the recognition engine in order to improve the solution provided by the system and then to decrease the word error rate. We achieved to decrease the word error rate of around 1%.
Moreover, one of our confidence measure acheived to improve comprehension of hard of hearing children.
In this thesis, we propose several confidence measures which are able to provide this estimation for applications using large vocabulary and on-the-fly recognition, as keyword indexation, broadcast news transcription, and live teaching class transcription for hard of hearing children.
In this framework, we have defined two types of confidence measures. The first, based on likelihood ratio, are frame-synchronous measures which can be computed simultaneously with the recognition process of the sentence. The second ones are based on an estimation of the posterior probability limited to a local neighborhood of the considered word, and need only a short delay before being computed on the sub word graph extracted from the recognition process.
These measures were assessed and compared to a state-of-the-art one, which is also based on posterior probability but which requires the recognition of the whole sentence. Two evaluations were performed on a real broadcast news corpus provided by the ESTER campaign. The first one used the Equal Error Rate criterion in an automatic transcription task. The second evaluation was performed in a keyword spotting task. We achieved performance close to our reference measure with our local measures and a delay of less than one second.
We also integrated one of our frame-synchronous measures in the decoding process of the recognition engine in order to improve the solution provided by the system and then to decrease the word error rate. We achieved to decrease the word error rate of around 1%.
Moreover, one of our confidence measure acheived to improve comprehension of hard of hearing children.
Url:
Links to Exploration step
Hal:tel-00185747Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Local and frame-synchronous confidence measures for automatic speech recognition</title>
<title xml:lang="fr">Mesure de confiance trame-synchrones et locales en reconnaissance automatique de la parole</title>
<author><name sortKey="Razik, Joseph" sort="Razik, Joseph" uniqKey="Razik J" first="Joseph" last="Razik">Joseph Razik</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-2359" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-160" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-300291" type="indirect"></relation>
<relation active="#struct-300292" type="indirect"></relation>
<relation active="#struct-300293" type="indirect"></relation>
<relation active="#struct-2496" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-160" type="direct"><org type="laboratory" xml:id="struct-160" status="OLD"><orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation name="UMR7503" active="#struct-441569" type="direct"></relation>
<relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-300291" type="direct"></relation>
<relation active="#struct-300292" type="direct"></relation>
<relation active="#struct-300293" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno>
<idno type="IdRef">02636817X</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300291" type="indirect"><org type="institution" xml:id="struct-300291" status="OLD"><orgName>Université Henri Poincaré - Nancy 1</orgName>
<orgName type="acronym">UHP</orgName>
<date type="end">2011-12-31</date>
<desc><address><addrLine>24-30 rue Lionnois, BP 60120, 54 003 NANCY cedex, France</addrLine>
<country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300292" type="indirect"><org type="institution" xml:id="struct-300292" status="OLD"><orgName>Université Nancy 2</orgName>
<date type="end">2011-12-31</date>
<desc><address><addrLine>91 avenue de la Libération, BP 454, 54001 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300293" type="indirect"><org type="institution" xml:id="struct-300293" status="OLD"><orgName>Institut National Polytechnique de Lorraine</orgName>
<orgName type="acronym">INPL</orgName>
<date type="end">2011-12-31</date>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-2496" type="direct"><org type="laboratory" xml:id="struct-2496" status="OLD"><orgName>INRIA Lorraine</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/centre-de-recherche-inria/nancy-grand-est</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:tel-00185747</idno>
<idno type="halId">tel-00185747</idno>
<idno type="halUri">https://tel.archives-ouvertes.fr/tel-00185747</idno>
<idno type="url">https://tel.archives-ouvertes.fr/tel-00185747</idno>
<date when="2007-10-09">2007-10-09</date>
<idno type="wicri:Area/Hal/Corpus">002F48</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Local and frame-synchronous confidence measures for automatic speech recognition</title>
<title xml:lang="fr">Mesure de confiance trame-synchrones et locales en reconnaissance automatique de la parole</title>
<author><name sortKey="Razik, Joseph" sort="Razik, Joseph" uniqKey="Razik J" first="Joseph" last="Razik">Joseph Razik</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-2359" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-160" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-300291" type="indirect"></relation>
<relation active="#struct-300292" type="indirect"></relation>
<relation active="#struct-300293" type="indirect"></relation>
<relation active="#struct-2496" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-160" type="direct"><org type="laboratory" xml:id="struct-160" status="OLD"><orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation name="UMR7503" active="#struct-441569" type="direct"></relation>
<relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-300291" type="direct"></relation>
<relation active="#struct-300292" type="direct"></relation>
<relation active="#struct-300293" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno>
<idno type="IdRef">02636817X</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300291" type="indirect"><org type="institution" xml:id="struct-300291" status="OLD"><orgName>Université Henri Poincaré - Nancy 1</orgName>
<orgName type="acronym">UHP</orgName>
<date type="end">2011-12-31</date>
<desc><address><addrLine>24-30 rue Lionnois, BP 60120, 54 003 NANCY cedex, France</addrLine>
<country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300292" type="indirect"><org type="institution" xml:id="struct-300292" status="OLD"><orgName>Université Nancy 2</orgName>
<date type="end">2011-12-31</date>
<desc><address><addrLine>91 avenue de la Libération, BP 454, 54001 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-300293" type="indirect"><org type="institution" xml:id="struct-300293" status="OLD"><orgName>Institut National Polytechnique de Lorraine</orgName>
<orgName type="acronym">INPL</orgName>
<date type="end">2011-12-31</date>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
<tutelle active="#struct-2496" type="direct"><org type="laboratory" xml:id="struct-2496" status="OLD"><orgName>INRIA Lorraine</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/centre-de-recherche-inria/nancy-grand-est</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>automatic speech recognition</term>
<term>confidence measure</term>
<term>frame-synchronous measure</term>
<term>hard of hearing people</term>
<term>keyword spotting</term>
<term>local measure</term>
</keywords>
<keywords scheme="mix" xml:lang="fr"><term>détection de mots-clés</term>
<term>malentendants</term>
<term>mesure de confiance</term>
<term>mesure locale</term>
<term>mesure trame-synchrone</term>
<term>reconnaissance automatique de la parole</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In automatic speech recognition, confidence measures aim at estimating the confidence we can give to a result (phone, word, sentence) provided by the speech recognition engine; for example, the contribution of the confidence measure allows to highlight the misrecognized or out-of-vocabulary words.
In this thesis, we propose several confidence measures which are able to provide this estimation for applications using large vocabulary and on-the-fly recognition, as keyword indexation, broadcast news transcription, and live teaching class transcription for hard of hearing children.
In this framework, we have defined two types of confidence measures. The first, based on likelihood ratio, are frame-synchronous measures which can be computed simultaneously with the recognition process of the sentence. The second ones are based on an estimation of the posterior probability limited to a local neighborhood of the considered word, and need only a short delay before being computed on the sub word graph extracted from the recognition process.
These measures were assessed and compared to a state-of-the-art one, which is also based on posterior probability but which requires the recognition of the whole sentence. Two evaluations were performed on a real broadcast news corpus provided by the ESTER campaign. The first one used the Equal Error Rate criterion in an automatic transcription task. The second evaluation was performed in a keyword spotting task. We achieved performance close to our reference measure with our local measures and a delay of less than one second.
We also integrated one of our frame-synchronous measures in the decoding process of the recognition engine in order to improve the solution provided by the system and then to decrease the word error rate. We achieved to decrease the word error rate of around 1%.
Moreover, one of our confidence measure acheived to improve comprehension of hard of hearing children.</div>
</front>
</TEI>
<hal api="V3"><titleStmt><title xml:lang="en">Local and frame-synchronous confidence measures for automatic speech recognition</title>
<title xml:lang="fr">Mesure de confiance trame-synchrones et locales en reconnaissance automatique de la parole</title>
<author role="aut"><persName><forename type="first">Joseph</forename>
<surname>Razik</surname>
</persName>
<email>Joseph.Razik@loria.fr</email>
<idno type="halauthor">66140</idno>
<affiliation ref="#struct-2359"></affiliation>
</author>
<editor role="depositor"><persName><forename>Joseph</forename>
<surname>Razik</surname>
</persName>
<email>Joseph.Razik@loria.fr</email>
</editor>
</titleStmt>
<editionStmt><edition n="v1"><date type="whenSubmitted">2007-11-06 23:41:13</date>
</edition>
<edition n="v2" type="current"><date type="whenSubmitted">2007-11-14 20:37:28</date>
<date type="whenModified">2016-05-19 01:14:09</date>
<date type="whenReleased">2007-11-15 07:22:06</date>
<date type="whenProduced">2007-10-09</date>
<date type="whenEndEmbargoed">2007-11-14</date>
<ref type="file" target="https://tel.archives-ouvertes.fr/tel-00185747v2/document"><date notBefore="2007-11-14"></date>
</ref>
<ref type="file" n="1" target="https://tel.archives-ouvertes.fr/tel-00185747/file/these_Joseph_Razik.pdf"><date notBefore="2007-11-14"></date>
</ref>
</edition>
<respStmt><resp>contributor</resp>
<name key="103949"><persName><forename>Joseph</forename>
<surname>Razik</surname>
</persName>
<email>Joseph.Razik@loria.fr</email>
</name>
</respStmt>
</editionStmt>
<publicationStmt><distributor>CCSD</distributor>
<idno type="halId">tel-00185747</idno>
<idno type="halUri">https://tel.archives-ouvertes.fr/tel-00185747</idno>
<idno type="halBibtex">razik:tel-00185747</idno>
<idno type="halRefHtml">Interface homme-machine [cs.HC]. Université Henri Poincaré - Nancy I, 2007. Français</idno>
<idno type="halRef">Interface homme-machine [cs.HC]. Université Henri Poincaré - Nancy I, 2007. Français</idno>
</publicationStmt>
<seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
<idno type="stamp" n="INPL">Institut National Polytechnique de Lorraine</idno>
<idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
<idno type="stamp" n="LORIA2">Publications du LORIA</idno>
<idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
<idno type="stamp" n="LORIA">LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
<idno type="stamp" n="LORIA-TALC" p="LORIA">Traitement automatique des langues et des connaissances</idno>
<idno type="stamp" n="INRIA2">INRIA 2</idno>
<idno type="stamp" n="INRIA-LORRAINE">INRIA Nancy - Grand Est</idno>
<idno type="stamp" n="LABO-LORIA-SET" p="LORIA">LABO-LORIA-SET</idno>
<idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
</seriesStmt>
<notesStmt></notesStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Local and frame-synchronous confidence measures for automatic speech recognition</title>
<title xml:lang="fr">Mesure de confiance trame-synchrones et locales en reconnaissance automatique de la parole</title>
<author role="aut"><persName><forename type="first">Joseph</forename>
<surname>Razik</surname>
</persName>
<email>Joseph.Razik@loria.fr</email>
<idno type="halAuthorId">66140</idno>
<affiliation ref="#struct-2359"></affiliation>
</author>
</analytic>
<monogr><imprint><date type="dateDefended">2007-10-09</date>
</imprint>
<authority type="institution">Université Henri Poincaré - Nancy I</authority>
<authority type="school">Informatique, Automatique, Électronique - Électrotechnique, Mathématiques</authority>
<authority type="supervisor">Jean-Paul Haton(Jean-Paul.Haton@loria.fr)</authority>
<authority type="jury">Jean-Paul Haton (directeur)</authority>
<authority type="jury">Odile Mella (co-directrice)</authority>
<authority type="jury">Jean-François Bonastre (rapporteur)</authority>
<authority type="jury">Gérard Chollet (rapporteur)</authority>
<authority type="jury">Laurent Besacier (examinateur)</authority>
<authority type="jury">René Schott (examinateur)</authority>
</monogr>
</biblStruct>
</sourceDesc>
<profileDesc><langUsage><language ident="fr">French</language>
</langUsage>
<textClass><keywords scheme="author"><term xml:lang="en">confidence measure</term>
<term xml:lang="en">frame-synchronous measure</term>
<term xml:lang="en">local measure</term>
<term xml:lang="en">keyword spotting</term>
<term xml:lang="en">automatic speech recognition</term>
<term xml:lang="en">hard of hearing people</term>
<term xml:lang="fr">mesure de confiance</term>
<term xml:lang="fr">mesure locale</term>
<term xml:lang="fr">mesure trame-synchrone</term>
<term xml:lang="fr">détection de mots-clés</term>
<term xml:lang="fr">reconnaissance automatique de la parole</term>
<term xml:lang="fr">malentendants</term>
</keywords>
<classCode scheme="halDomain" n="info.info-hc">Computer Science [cs]/Human-Computer Interaction [cs.HC]</classCode>
<classCode scheme="halDomain" n="info.info-oh">Computer Science [cs]/Other [cs.OH]</classCode>
<classCode scheme="halTypology" n="THESE">Theses</classCode>
</textClass>
<abstract xml:lang="en">In automatic speech recognition, confidence measures aim at estimating the confidence we can give to a result (phone, word, sentence) provided by the speech recognition engine; for example, the contribution of the confidence measure allows to highlight the misrecognized or out-of-vocabulary words.
In this thesis, we propose several confidence measures which are able to provide this estimation for applications using large vocabulary and on-the-fly recognition, as keyword indexation, broadcast news transcription, and live teaching class transcription for hard of hearing children.
In this framework, we have defined two types of confidence measures. The first, based on likelihood ratio, are frame-synchronous measures which can be computed simultaneously with the recognition process of the sentence. The second ones are based on an estimation of the posterior probability limited to a local neighborhood of the considered word, and need only a short delay before being computed on the sub word graph extracted from the recognition process.
These measures were assessed and compared to a state-of-the-art one, which is also based on posterior probability but which requires the recognition of the whole sentence. Two evaluations were performed on a real broadcast news corpus provided by the ESTER campaign. The first one used the Equal Error Rate criterion in an automatic transcription task. The second evaluation was performed in a keyword spotting task. We achieved performance close to our reference measure with our local measures and a delay of less than one second.
We also integrated one of our frame-synchronous measures in the decoding process of the recognition engine in order to improve the solution provided by the system and then to decrease the word error rate. We achieved to decrease the word error rate of around 1%.
Moreover, one of our confidence measure acheived to improve comprehension of hard of hearing children.</abstract>
<abstract xml:lang="fr">En reconnaissance automatique de la parole, les mesures de confiance tentent d'estimer la confiance qu'on peut accorder au résultat (phonème, mot, phrase) fourni par le moteur de reconnaissance ; l'apport de la mesure de confiance permettant par exemple de mettre en évidence les mots mal reconnus ou hors vocabulaire.
Dans cette thèse nous proposons des mesures de confiance capables de faire cette estimation dans le cas d'applications nécessitant une reconnaissance "grand vocabulaire" en flux continu comme l'indexation en mots clés ou la transcription en ligne d'émissions radiophoniques et télévisuelles, ou bien encore la transcription du cours d'un enseignant dans une salle de classe pour des élèves malentendants.
Dans ce cadre, nous avons défini deux types de mesure de confiance. Les premières, fondées sur des rapports de vraisemblance, sont des mesures trame-synchrones qui peuvent être calculées au fur et à mesure de la progression du moteur de reconnaissance au sein de la phrase à reconnaître. Les secondes, fondées sur une estimation de la probabilité a posteriori limitée à un voisinage local du mot considéré, nécessitent seulement un court délai avant de pouvoir être calculées.
Ces mesures ont été évaluées et comparées à une mesure de l'état de l'art également fondée sur la probabilité a posteriori mais nécessitant la reconnaissance de toute la phrase. Cette évaluation a été faite d'une part dans une tâche de transcription automatique d'un corpus réel d'émissions radiophoniques issu de la campagne ESTER et en utilisant le critère d'évaluation EER (Equal Error Rate) ; d'autre part dans une tâche de détection de mots clés sur le même corpus. Des performances très proches de celles de la mesure de l'état de l'art ont été obtenues par nos mesures locales avec un délai de moins d'une seconde.
Nous avons également intégré l'une de nos mesures trame-synchrones dans le processus de décodage du moteur de reconnaissance afin d'améliorer la solution proposée par le système et ainsi diminuer le taux d'erreur en mots d'environ 6% en relatif.
Enfin, une de nos mesures de confiance a permis par la mise en valeur de mots de faible confiance d'améliorer la compréhension de malentendants.</abstract>
</profileDesc>
</hal>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Hal/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002F48 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Corpus/biblio.hfd -nk 002F48 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Hal |étape= Corpus |type= RBID |clé= Hal:tel-00185747 |texte= Local and frame-synchronous confidence measures for automatic speech recognition }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |