Inversion acoustique articulatoire par une méthode variationnelle
Identifieur interne : 002417 ( Crin/Checkpoint ); précédent : 002416; suivant : 002418Inversion acoustique articulatoire par une méthode variationnelle
Auteurs : Yves Laprie ; Bruno MathieuSource :
English descriptors
- KwdEn :
Abstract
This paper presents a novel approach to recovering articulatory trajectories from the speech signal using a variational calculus method and Maeda's articulatory model. The acoustic-to-articulatory mapping is generally assessed by a double criterion : the acoustic proximity of results to acoustic data and the smoothness of articulatory trajectories. Most of the existing methods are unable to exploit the two criteria simultaneously or at least at the same level. On the other hand, our variational calculus approach combines the two criteria simultaneously and ensures the global acoustic and articulatory consistency without further optimization. This method gives rise to an iterative process which optimizes a startup solution given by an improved lookup algorithm. Codebooks generated with an articulatory model show nonuniform sampling of the acoustic space due to nonlinearities of the acoustic-to-articulatory mapping. We therefore designed an improved lookup algorithm building realistic articulatory trajectories which are not necessarily defined throughout the speech signal.
Links toward previous steps (curation, corpus...)
Links to Exploration step
CRIN:laprie98dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="170">Inversion acoustique articulatoire par une méthode variationnelle</title></titleStmt><publicationStmt><idno type="RBID">CRIN:laprie98d</idno><date when="1998" year="1998">1998</date><idno type="wicri:Area/Crin/Corpus">002109</idno><idno type="wicri:Area/Crin/Curation">002109</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">002109</idno><idno type="wicri:Area/Crin/Checkpoint">002417</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002417</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Inversion acoustique articulatoire par une méthode variationnelle</title><author><name sortKey="Laprie, Yves" sort="Laprie, Yves" uniqKey="Laprie Y" first="Yves" last="Laprie">Yves Laprie</name></author><author><name sortKey="Mathieu, Bruno" sort="Mathieu, Bruno" uniqKey="Mathieu B" first="Bruno" last="Mathieu">Bruno Mathieu</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>articulatory model</term><term>inversion</term><term>variational</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="3601">This paper presents a novel approach to recovering articulatory trajectories from the speech signal using a variational calculus method and Maeda's articulatory model. The acoustic-to-articulatory mapping is generally assessed by a double criterion : the acoustic proximity of results to acoustic data and the smoothness of articulatory trajectories. Most of the existing methods are unable to exploit the two criteria simultaneously or at least at the same level. On the other hand, our variational calculus approach combines the two criteria simultaneously and ensures the global acoustic and articulatory consistency without further optimization. This method gives rise to an iterative process which optimizes a startup solution given by an improved lookup algorithm. Codebooks generated with an articulatory model show nonuniform sampling of the acoustic space due to nonlinearities of the acoustic-to-articulatory mapping. We therefore designed an improved lookup algorithm building realistic articulatory trajectories which are not necessarily defined throughout the speech signal.</div></front></TEI><BibTex type="inproceedings"><ref>laprie98d</ref><crinnumber>98-R-049</crinnumber><category>3</category><equipe>RFIA</equipe><author><e>Laprie, Yves</e><e>Mathieu, Bruno</e></author><title>Inversion acoustique articulatoire par une méthode variationnelle</title><booktitle>{Journées d'Etudes sur la Parole, Martigny, Suisse}</booktitle><year>1998</year><month>jun</month><url>http://www.loria.fr/publications/1998/98-R-049/98-R-049.ps</url><keywords><e>inversion</e><e>variational</e><e>articulatory model</e></keywords><abstract>This paper presents a novel approach to recovering articulatory trajectories from the speech signal using a variational calculus method and Maeda's articulatory model. The acoustic-to-articulatory mapping is generally assessed by a double criterion : the acoustic proximity of results to acoustic data and the smoothness of articulatory trajectories. Most of the existing methods are unable to exploit the two criteria simultaneously or at least at the same level. On the other hand, our variational calculus approach combines the two criteria simultaneously and ensures the global acoustic and articulatory consistency without further optimization. This method gives rise to an iterative process which optimizes a startup solution given by an improved lookup algorithm. Codebooks generated with an articulatory model show nonuniform sampling of the acoustic space due to nonlinearities of the acoustic-to-articulatory mapping. We therefore designed an improved lookup algorithm building realistic articulatory trajectories which are not necessarily defined throughout the speech signal.</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 002417 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Checkpoint/biblio.hfd -nk 002417 | 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:laprie98d
|texte= Inversion acoustique articulatoire par une méthode variationnelle
}}
| This area was generated with Dilib version V0.6.33. |  |