Explicit trajectories and speaker class modeling for child and adult speech recognition
Identifieur interne : 002118 ( Hal/Corpus ); précédent : 002117; suivant : 002119Explicit trajectories and speaker class modeling for child and adult speech recognition
Auteurs : Arseniy Gorin ; Denis JouvetSource :
Descripteurs français
- mix :
English descriptors
- mix :
Abstract
When the speech data is produced by speakers of different age and gender, the acoustic variability of any given phonetic unit becomes large, which degrades speech recognition performance. One way to go beyond conventional Hidden Markov Model is to explicitly include speaker class information in the modeling. Speaker classes can be obtained automatically, and they are used for building speaker class-specific acoustic models. This paper introduces a structuring of the Gaussian components of the GMM densities with respect to the speaker classes. In a first approach, this structuring of the Gaussian components is completed with speaker class-dependent mixture weights, and in a second approach, with transition matrices, which add dependencies between Gaussian components of mixture densities (as in stranded GMMs). The two approaches bring substantial performance improvements when recognizing adult and child speech. Using class-structured components plus mixture transition matrices reduces by more than one third the word error rate on the TIDIGIT corpus.
Url:
Links to Exploration step
Hal:hal-01080343Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Explicit trajectories and speaker class modeling for child and adult speech recognition</title>
<title xml:lang="fr">Modélisation de trajectoires et de classes de locuteurs pour la reconnaissance de voix d'enfants et d'adultes</title>
<author><name sortKey="Gorin, Arseniy" sort="Gorin, Arseniy" uniqKey="Gorin A" first="Arseniy" last="Gorin">Arseniy Gorin</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205127" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<date type="end">2014-06-30</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</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/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</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-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<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 active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</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>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Jouvet, Denis" sort="Jouvet, Denis" uniqKey="Jouvet D" first="Denis" last="Jouvet">Denis Jouvet</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205127" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<date type="end">2014-06-30</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</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/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</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-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<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 active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</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>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-01080343</idno>
<idno type="halId">hal-01080343</idno>
<idno type="halUri">https://hal.inria.fr/hal-01080343</idno>
<idno type="url">https://hal.inria.fr/hal-01080343</idno>
<date when="2014-06-23">2014-06-23</date>
<idno type="wicri:Area/Hal/Corpus">002118</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Explicit trajectories and speaker class modeling for child and adult speech recognition</title>
<title xml:lang="fr">Modélisation de trajectoires et de classes de locuteurs pour la reconnaissance de voix d'enfants et d'adultes</title>
<author><name sortKey="Gorin, Arseniy" sort="Gorin, Arseniy" uniqKey="Gorin A" first="Arseniy" last="Gorin">Arseniy Gorin</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205127" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<date type="end">2014-06-30</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</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/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</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-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<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 active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</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>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
<author><name sortKey="Jouvet, Denis" sort="Jouvet, Denis" uniqKey="Jouvet D" first="Denis" last="Jouvet">Denis Jouvet</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205127" status="OLD"><idno type="RNSR">200118295L</idno>
<orgName>Analysis, perception and recognition of speech</orgName>
<orgName type="acronym">PAROLE</orgName>
<date type="end">2014-06-30</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/parole</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</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/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</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-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<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 active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</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>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>Speech recognition</term>
<term>speaker class modeling</term>
<term>stochastic trajectory modeling.</term>
<term>unsupervised clustering</term>
</keywords>
<keywords scheme="mix" xml:lang="fr"><term>Reconnaissance de la parole</term>
<term>classification non supervisée</term>
<term>modèles de classes de locuteurs</term>
<term>modèles stochastiques de trajectoire.</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">When the speech data is produced by speakers of different age and gender, the acoustic variability of any given phonetic unit becomes large, which degrades speech recognition performance. One way to go beyond conventional Hidden Markov Model is to explicitly include speaker class information in the modeling. Speaker classes can be obtained automatically, and they are used for building speaker class-specific acoustic models. This paper introduces a structuring of the Gaussian components of the GMM densities with respect to the speaker classes. In a first approach, this structuring of the Gaussian components is completed with speaker class-dependent mixture weights, and in a second approach, with transition matrices, which add dependencies between Gaussian components of mixture densities (as in stranded GMMs). The two approaches bring substantial performance improvements when recognizing adult and child speech. Using class-structured components plus mixture transition matrices reduces by more than one third the word error rate on the TIDIGIT corpus.</div>
</front>
</TEI>
<hal api="V3"><titleStmt><title xml:lang="en">Explicit trajectories and speaker class modeling for child and adult speech recognition</title>
<title xml:lang="fr">Modélisation de trajectoires et de classes de locuteurs pour la reconnaissance de voix d'enfants et d'adultes</title>
<author role="aut"><persName><forename type="first">Arseniy</forename>
<surname>Gorin</surname>
</persName>
<email>arseniy.gorin@inria.fr</email>
<idno type="halauthor">1093424</idno>
<affiliation ref="#struct-205127"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Denis</forename>
<surname>Jouvet</surname>
</persName>
<email>denis.jouvet@inria.fr</email>
<idno type="halauthor">1093425</idno>
<affiliation ref="#struct-205127"></affiliation>
</author>
<editor role="depositor"><persName><forename>Denis</forename>
<surname>Jouvet</surname>
</persName>
<email>denis.jouvet@inria.fr</email>
</editor>
</titleStmt>
<editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2014-11-05 09:29:03</date>
<date type="whenModified">2015-09-22 01:12:54</date>
<date type="whenReleased">2014-11-05 09:52:00</date>
<date type="whenProduced">2014-06-23</date>
<date type="whenEndEmbargoed">2014-11-05</date>
<ref type="file" target="https://hal.inria.fr/hal-01080343/document"><date notBefore="2014-11-05"></date>
</ref>
<ref type="file" subtype="author" n="1" target="https://hal.inria.fr/hal-01080343/file/jep2014-agorin-V5-FR-V.01.pdf"><date notBefore="2014-11-05"></date>
</ref>
</edition>
<respStmt><resp>contributor</resp>
<name key="155601"><persName><forename>Denis</forename>
<surname>Jouvet</surname>
</persName>
<email>denis.jouvet@inria.fr</email>
</name>
</respStmt>
</editionStmt>
<publicationStmt><distributor>CCSD</distributor>
<idno type="halId">hal-01080343</idno>
<idno type="halUri">https://hal.inria.fr/hal-01080343</idno>
<idno type="halBibtex">gorin:hal-01080343</idno>
<idno type="halRefHtml">XXXème édition des Journées d'Etudes sur la Parole, Jun 2014, Le Mans, France. 2014</idno>
<idno type="halRef">XXXème édition des Journées d'Etudes sur la Parole, Jun 2014, Le Mans, France. 2014</idno>
</publicationStmt>
<seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
<idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
<idno type="stamp" n="INRIA-LORRAINE">INRIA Nancy - Grand Est</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-TALC" p="LORIA">Traitement automatique des langues et des connaissances</idno>
<idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
<idno type="stamp" n="LORIA">LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
<idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
</seriesStmt>
<notesStmt><note type="audience" n="2">International</note>
<note type="invited" n="0">No</note>
<note type="popular" n="0">No</note>
<note type="peer" n="1">Yes</note>
<note type="proceedings" n="1">Yes</note>
</notesStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Explicit trajectories and speaker class modeling for child and adult speech recognition</title>
<title xml:lang="fr">Modélisation de trajectoires et de classes de locuteurs pour la reconnaissance de voix d'enfants et d'adultes</title>
<author role="aut"><persName><forename type="first">Arseniy</forename>
<surname>Gorin</surname>
</persName>
<email>arseniy.gorin@inria.fr</email>
<idno type="halAuthorId">1093424</idno>
<affiliation ref="#struct-205127"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Denis</forename>
<surname>Jouvet</surname>
</persName>
<email>denis.jouvet@inria.fr</email>
<idno type="halAuthorId">1093425</idno>
<affiliation ref="#struct-205127"></affiliation>
</author>
</analytic>
<monogr><meeting><title>XXXème édition des Journées d'Etudes sur la Parole</title>
<date type="start">2014-06-23</date>
<date type="end">2014-06-27</date>
<settlement>Le Mans</settlement>
<country key="FR">France</country>
</meeting>
<imprint><date type="datePub">2014-06-23</date>
</imprint>
</monogr>
</biblStruct>
</sourceDesc>
<profileDesc><langUsage><language ident="fr">French</language>
</langUsage>
<textClass><keywords scheme="author"><term xml:lang="en">Speech recognition</term>
<term xml:lang="en">unsupervised clustering</term>
<term xml:lang="en">speaker class modeling</term>
<term xml:lang="en">stochastic trajectory modeling.</term>
<term xml:lang="fr">Reconnaissance de la parole</term>
<term xml:lang="fr">classification non supervisée</term>
<term xml:lang="fr">modèles de classes de locuteurs</term>
<term xml:lang="fr">modèles stochastiques de trajectoire.</term>
</keywords>
<classCode scheme="halDomain" n="info.info-ts">Computer Science [cs]/Signal and Image Processing</classCode>
<classCode scheme="halTypology" n="COMM">Conference papers</classCode>
</textClass>
<abstract xml:lang="en">When the speech data is produced by speakers of different age and gender, the acoustic variability of any given phonetic unit becomes large, which degrades speech recognition performance. One way to go beyond conventional Hidden Markov Model is to explicitly include speaker class information in the modeling. Speaker classes can be obtained automatically, and they are used for building speaker class-specific acoustic models. This paper introduces a structuring of the Gaussian components of the GMM densities with respect to the speaker classes. In a first approach, this structuring of the Gaussian components is completed with speaker class-dependent mixture weights, and in a second approach, with transition matrices, which add dependencies between Gaussian components of mixture densities (as in stranded GMMs). The two approaches bring substantial performance improvements when recognizing adult and child speech. Using class-structured components plus mixture transition matrices reduces by more than one third the word error rate on the TIDIGIT corpus.</abstract>
<abstract xml:lang="fr">RÉSUMÉ Lorsque l'on considère de la parole produite par des enfants et des adultes, la variabilité acous-tique de chaque unité phonétique devient grande, ce qui dégrade les performances de recon-naissance. Un moyen d'aller au-delà des modèles de Markov traditionnels, est de prendre en considération des classes de locuteurs. Les classes de locuteurs peuvent être obtenues automa-tiquement. Elles servent à fabriquer des modèles acoustiques spécifiques de chaque classe. Ce papier propose une structuration des composantes des densités multigaussiennes (GMMs) en re-lation avec des classes de locuteurs. Dans une première approche, cette structuration des densités est complétée par des pondérations des composantes gaussiennes dépendantes des classes de locuteurs, et dans une deuxième approche, par des matrices de transition entre les composantes gaussiennes des densités (comme dans les stranded GMMs). Ces deux approches apportent des gains substantiels pour la reconnaissance de voix d'enfants et d'adultes. La structuration des composantes gaussiennes complétée par des matrices de transition entre composantes réduit de plus d'un tiers le taux d'erreur mot sur le corpus TIDIGIT.</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 002118 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Corpus/biblio.hfd -nk 002118 | 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:hal-01080343 |texte= Explicit trajectories and speaker class modeling for child and adult speech recognition }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |