Détection du fondamental de la parole en temps réel : application aux voix pathologiques
Identifieur interne : 001162 ( Main/Exploration ); précédent : 001161; suivant : 001163Détection du fondamental de la parole en temps réel : application aux voix pathologiques
Auteurs : Fadoua Bahja [Maroc]Source :
Descripteurs français
- mix :
Abstract
This thesis is part of researches aimed at determining the fundamental frequency of speech signals. The first contribution is related to the development of real time pitch detector algorithms, based on an implicit circular autocorrelation of the glottal excitation. Among all the pitch detection algorithms described in the literature, few of them are able to tackle correctly all the problems of pitch tracking. For this reason, we expanded our scope of investigation and proposed new algorithms based on wavelet transforms. To evaluate the performances of the proposed algorithms, we used two databases : Bagshaw and Keele. The results we obtained prove that our developed algorithms compare favourably with the best reference pitch detector algorithms described in the literature. The second contribution of this thesis concerns the implementation of a voice conversion system in order to enhance the pathological voice. In this case, we talk about a correction system. Our main contribution, concerning voice conversion, lies in the prediction of Fourier cepstral coefficients related to the excitation signal. This new kind of prediction allowed us to implement conversion systems whose results, either they are objective or subjective, validate the proposed approach.
Url:
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Hal, to step Corpus: 005A77
- to stream Hal, to step Curation: 005A77
- to stream Hal, to step Checkpoint: 001078
- to stream Main, to step Merge: 001173
- to stream Main, to step Curation: 001162
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="fr">Détection du fondamental de la parole en temps réel : application aux voix pathologiques</title><author><name sortKey="Bahja, Fadoua" sort="Bahja, Fadoua" uniqKey="Bahja F" first="Fadoua" last="Bahja">Fadoua Bahja</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-176072" status="OLD"><orgName>Laboratoire LRIT, CNRST URAC 29</orgName><desc><address><addrLine>Rabat, Morocco</addrLine><country key="MA"></country></address></desc><listRelation><relation active="#struct-301054" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-301054" type="direct"><org type="institution" xml:id="struct-301054" status="VALID"><orgName>Université Mohammed 5 Agdal</orgName><desc><address><country key="MA"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Maroc</country></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">HAL</idno><idno type="RBID">Hal:tel-00927147</idno><idno type="halId">tel-00927147</idno><idno type="halUri">https://tel.archives-ouvertes.fr/tel-00927147</idno><idno type="url">https://tel.archives-ouvertes.fr/tel-00927147</idno><date when="2013-06-15">2013-06-15</date><idno type="wicri:Area/Hal/Corpus">005A77</idno><idno type="wicri:Area/Hal/Curation">005A77</idno><idno type="wicri:Area/Hal/Checkpoint">001078</idno><idno type="wicri:explorRef" wicri:stream="Hal" wicri:step="Checkpoint">001078</idno><idno type="wicri:Area/Main/Merge">001173</idno><idno type="wicri:Area/Main/Curation">001162</idno><idno type="wicri:Area/Main/Exploration">001162</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="fr">Détection du fondamental de la parole en temps réel : application aux voix pathologiques</title><author><name sortKey="Bahja, Fadoua" sort="Bahja, Fadoua" uniqKey="Bahja F" first="Fadoua" last="Bahja">Fadoua Bahja</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-176072" status="OLD"><orgName>Laboratoire LRIT, CNRST URAC 29</orgName><desc><address><addrLine>Rabat, Morocco</addrLine><country key="MA"></country></address></desc><listRelation><relation active="#struct-301054" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-301054" type="direct"><org type="institution" xml:id="struct-301054" status="VALID"><orgName>Université Mohammed 5 Agdal</orgName><desc><address><country key="MA"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Maroc</country></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="mix" xml:lang="fr"><term>Fréquence fondamentale</term><term>auto corrélation circulaire</term><term>classification de voisement</term><term>conversion de voix</term><term>correction de voix</term><term>excitation cepstrale</term><term>impulsion cepstrale</term><term>modèle de mélange Gaussien</term><term>période de pitch</term><term>quantification vectorielle</term><term>temps-réel</term><term>transformation en ondelettes</term><term>vote majoritaire</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This thesis is part of researches aimed at determining the fundamental frequency of speech signals. The first contribution is related to the development of real time pitch detector algorithms, based on an implicit circular autocorrelation of the glottal excitation. Among all the pitch detection algorithms described in the literature, few of them are able to tackle correctly all the problems of pitch tracking. For this reason, we expanded our scope of investigation and proposed new algorithms based on wavelet transforms. To evaluate the performances of the proposed algorithms, we used two databases : Bagshaw and Keele. The results we obtained prove that our developed algorithms compare favourably with the best reference pitch detector algorithms described in the literature. The second contribution of this thesis concerns the implementation of a voice conversion system in order to enhance the pathological voice. In this case, we talk about a correction system. Our main contribution, concerning voice conversion, lies in the prediction of Fourier cepstral coefficients related to the excitation signal. This new kind of prediction allowed us to implement conversion systems whose results, either they are objective or subjective, validate the proposed approach.</div></front></TEI><affiliations><list><country><li>Maroc</li></country></list><tree><country name="Maroc"><noRegion><name sortKey="Bahja, Fadoua" sort="Bahja, Fadoua" uniqKey="Bahja F" first="Fadoua" last="Bahja">Fadoua Bahja</name></noRegion></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 001162 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001162 | 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= Hal:tel-00927147
|texte= Détection du fondamental de la parole en temps réel : application aux voix pathologiques
}}
| This area was generated with Dilib version V0.6.33. |  |