<?xml version="1.0" encoding="UTF-8"?><mets:mets xmlns:mads="http://www.loc.gov/mads/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:tef="http://www.abes.fr/abes/documents/tef" xmlns:metsRights="http://cosimo.stanford.edu/sdr/metsrights/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mets="http://www.loc.gov/METS/">
    <mets:metsHdr ID="rennes1-ori-wf-1-21588" CREATEDATE="2025-10-03T17:13:52" LASTMODDATE="2025-10-03T17:13:53">
  <mets:agent ROLE="CREATOR">
            <mets:name>Université de Rennes</mets:name>
        </mets:agent>
</mets:metsHdr>
    <mets:dmdSec ID="desc_expr" CREATED="2025-10-03T17:13:52">
  <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_these">
            <mets:xmlData>
                <tef:thesisRecord>
     <dc:title xml:lang="fr">Compression audio monocanal par apprentissage profond</dc:title>
     <dcterms:alternative xml:lang="en">Mono audio coding with deep learning</dcterms:alternative>
     <dc:subject xml:lang="fr">codage audio neuronal</dc:subject><dc:subject xml:lang="fr">qualité audio</dc:subject><dc:subject xml:lang="fr">quantification espace latent</dc:subject>
     <dc:subject xml:lang="en">neural audio coding</dc:subject><dc:subject xml:lang="en">audio quality</dc:subject><dc:subject xml:lang="en">latent space quantization</dc:subject>
     <tef:sujetRameau><tef:vedetteRameauNomCommun>
						<tef:elementdEntree autoriteSource="Sudoc" autoriteExterne="052570673">Compression audio</tef:elementdEntree>
					</tef:vedetteRameauNomCommun><tef:vedetteRameauNomCommun>
						<tef:elementdEntree autoriteSource="Sudoc" autoriteExterne="030971098">Réseaux neuronaux (informatique)</tef:elementdEntree>
					</tef:vedetteRameauNomCommun><tef:vedetteRameauNomCommun>
						<tef:elementdEntree autoriteSource="Sudoc" autoriteExterne="223540633">Apprentissage profond</tef:elementdEntree>
					</tef:vedetteRameauNomCommun></tef:sujetRameau>
     
     
     <dcterms:abstract xml:lang="fr">Le domaine de la compression audio, au cœur des applications de transmission et de stockage de la parole, musique et audio général, est bouleversé depuis quelques années par l'utilisation des réseaux de neurones artificiels. La nouvelle génération de codecs qui en découle, les codecs audio neuronaux, démontre des performances très prometteuses, en particulier par leur capacité à compresser à très bas débit. Dans cette thèse nous nous intéressons au potentiel des codecs audio neuronaux selon deux angles principaux. Le premier concerne la qualité audio permise par ces codecs et les moyens de la mesurer. Nous proposons des caractérisations étendues de la qualité des codecs neuronaux sur la parole ainsi que la musique et le contenu mixte parole/musique. Ces résultats issus de tests subjectifs sont également employés pour évaluer l'estimation de qualité proposée par les outils de mesure automatique que sont les métriques objectives. Le second axe de travail est dédié à l'analyse et la quantification de l'espace latent des codecs audio neuronaux. Une étude de l'espace latent appris par un codec neuronal nous permet d'optimiser l'étage de quantification du codec. Enfin, nous explorons l'utilisation de la quantification vectorielle sphérique par réseau de points dans le cadre du codage audio neuronal et montrons qu'il s'agit d'une alternative avantageuse d'un point de vue apprentissage, complexité calculatoire et stockage mémoire.</dcterms:abstract>
     <dcterms:abstract xml:lang="en">The field of audio coding, which lies at the heart of applications for transmitting and storing speech, music, and general audio, has been revolutionized in recent years by the use of artificial neural networks. The resulting new generation of codecs, known as neural audio codecs, show very promising performance, particularly in terms of their ability to compress at very low bit rates. In this thesis, we examine the potential of neural audio codecs from two main angles. The first deals with the audio quality enabled by these codecs and the means of measuring it. We propose extensive evaluations of the quality of neural codecs for speech, music, and mixed speech/music content. These subjective tests are also used to evaluate the quality estimates provided by objective models for automatic measurement. The second area of work is dedicated to the analysis and quantization of neural audio codecs latent space. A study of the latent space learned by a neural codec allows us to optimize the quantization stage of the codec. Finally, we explore the use of spherical lattice vector quantization in the context of neural audio coding and show that it is an advantageous alternative in terms of training, computational complexity and memory storage.</dcterms:abstract>
     <dc:type>Electronic Thesis or Dissertation</dc:type><dc:type xsi:type="dcterms:DCMIType">Text</dc:type>
     <dc:language xsi:type="dcterms:RFC3066">fr</dc:language>
    </tef:thesisRecord>
            </mets:xmlData>
        </mets:mdWrap>
</mets:dmdSec>
    <mets:dmdSec ID="desc_edition" CREATED="2025-10-03T17:13:52">
  <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_edition">
            <mets:xmlData>
                <tef:edition><dcterms:medium xsi:type="dcterms:IMT">application/pdf</dcterms:medium><dcterms:extent>1 : 5977 Ko</dcterms:extent><dc:identifier xsi:type="dcterms:URI">https://ged.univ-rennes1.fr/nuxeo/site/esupversions/22c0a665-0da9-475e-ac17-264b5771e4fd</dc:identifier></tef:edition>
            </mets:xmlData>
        </mets:mdWrap>
</mets:dmdSec>
    <mets:amdSec>
        <mets:techMD ID="admin_expr">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_admin_these">
                <mets:xmlData>
                    <tef:thesisAdmin>
                        <tef:auteur>
       <tef:nom>Muller</tef:nom>
       <tef:prenom>Thomas</tef:prenom>
       
       <tef:dateNaissance>1999-03-16</tef:dateNaissance>
       <tef:nationalite scheme="ISO-3166-1">FR</tef:nationalite>
       <tef:autoriteExterne autoriteSource="Sudoc">296469394</tef:autoriteExterne>
       <tef:autoriteExterne autoriteSource="mailPerso">thomas.muller63@orange.fr</tef:autoriteExterne>
      </tef:auteur>
                        <dc:identifier xsi:type="tef:NNT">2025URENS093</dc:identifier>
                        <dc:identifier xsi:type="tef:nationalThesisPID">http://www.theses.fr/2025URENS093</dc:identifier>
                        <dcterms:dateAccepted xsi:type="dcterms:W3CDTF">2025-12-11</dcterms:dateAccepted>
                        <tef:thesis.degree>
                            <tef:thesis.degree.discipline xml:lang="fr">Signal, image, vision</tef:thesis.degree.discipline>
                            <tef:thesis.degree.grantor>
        <tef:nom>Université de Rennes</tef:nom><tef:autoriteInterne>thesis.degree.grantor_1</tef:autoriteInterne>
        
        <tef:autoriteExterne autoriteSource="Sudoc">26693823X</tef:autoriteExterne>
       </tef:thesis.degree.grantor>
                            <tef:thesis.degree.level>Doctorat</tef:thesis.degree.level>
                        </tef:thesis.degree>
                        <tef:theseSurTravaux>non</tef:theseSurTravaux>
                        <tef:avisJury>oui</tef:avisJury><tef:directeurThese><tef:nom>Scalart</tef:nom><tef:prenom>Pascal</tef:prenom><tef:autoriteInterne>intervenant_1</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">06985582X</tef:autoriteExterne></tef:directeurThese><tef:presidentJury><tef:nom>Lagrange</tef:nom><tef:prenom>Mathieu</tef:prenom><tef:autoriteInterne>intervenant_2</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">083993339</tef:autoriteExterne></tef:presidentJury><tef:membreJury><tef:nom>Leglaive</tef:nom><tef:prenom>Simon</tef:prenom><tef:autoriteInterne>intervenant_3</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">25312171X</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Tahon</tef:nom><tef:prenom>Marie</tef:prenom><tef:autoriteInterne>intervenant_4</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">165065532</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Ragot</tef:nom><tef:prenom>Stéphane</tef:prenom><tef:autoriteInterne>intervenant_5</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">136843778</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Philippe</tef:nom><tef:prenom>Pierrick</tef:prenom><tef:autoriteInterne>intervenant_6</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">078760941</tef:autoriteExterne></tef:membreJury><tef:rapporteur><tef:nom>Farrugia</tef:nom><tef:prenom>Nicolas</tef:prenom><tef:autoriteInterne>intervenant_7</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">133684733</tef:autoriteExterne></tef:rapporteur><tef:rapporteur><tef:nom>Girin</tef:nom><tef:prenom>Laurent</tef:prenom><tef:autoriteInterne>intervenant_8</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">088998037</tef:autoriteExterne></tef:rapporteur>
      
      
      
      
      
      
      
      
      
                        
                        <tef:ecoleDoctorale>
       <tef:nom>MATISSE</tef:nom><tef:autoriteInterne>ecoleDoctorale_1</tef:autoriteInterne>
       
       <tef:autoriteExterne autoriteSource="Sudoc">267602553</tef:autoriteExterne>
      </tef:ecoleDoctorale>
                        <tef:partenaireRecherche type="laboratoire">
       <tef:nom>
IRISA
</tef:nom><tef:autoriteInterne>partenaireRecherche_1</tef:autoriteInterne>
       
       <tef:autoriteExterne autoriteSource="Sudoc">
026386909
</tef:autoriteExterne>
      </tef:partenaireRecherche>
                        <tef:oaiSetSpec>ddc:620</tef:oaiSetSpec>
                        
                        
                        
                    <tef:MADSAuthority authorityID="intervenant_1" type="personal"><tef:personMADS><mads:namePart type="family">Scalart</mads:namePart><mads:namePart type="given">Pascal</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_2" type="personal"><tef:personMADS><mads:namePart type="family">Lagrange</mads:namePart><mads:namePart type="given">Mathieu</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_3" type="personal"><tef:personMADS><mads:namePart type="family">Leglaive</mads:namePart><mads:namePart type="given">Simon</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_4" type="personal"><tef:personMADS><mads:namePart type="family">Tahon</mads:namePart><mads:namePart type="given">Marie</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_5" type="personal"><tef:personMADS><mads:namePart type="family">Ragot</mads:namePart><mads:namePart type="given">Stéphane</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_6" type="personal"><tef:personMADS><mads:namePart type="family">Philippe</mads:namePart><mads:namePart type="given">Pierrick</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_7" type="personal"><tef:personMADS><mads:namePart type="family">Farrugia</mads:namePart><mads:namePart type="given">Nicolas</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_8" type="personal"><tef:personMADS><mads:namePart type="family">Girin</mads:namePart><mads:namePart type="given">Laurent</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="thesis.degree.grantor_1" type="corporate"><tef:personMADS><mads:namePart>Université de Rennes</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="ecoleDoctorale_1" type="corporate"><tef:personMADS><mads:namePart>MATISSE</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="partenaireRecherche_1" type="corporate"><tef:personMADS><mads:namePart>
IRISA
</mads:namePart></tef:personMADS></tef:MADSAuthority></tef:thesisAdmin>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:techMD><mets:techMD ID="file_1"><mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_tech_fichier"><mets:xmlData><tef:meta_fichier>
     <tef:encodage>ASCII</tef:encodage>
     <tef:formatFichier>PDF</tef:formatFichier>
     
     
     
     <tef:taille>6120000</tef:taille>
    </tef:meta_fichier></mets:xmlData></mets:mdWrap></mets:techMD>
        
        <mets:rightsMD ID="dr_expr_thesard">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_auteur_these">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
        <mets:rightsMD ID="dr_expr_univ">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_etablissement_these">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
        <mets:rightsMD ID="dr_version">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_version">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
    </mets:amdSec>
    <mets:fileSec>
  <mets:fileGrp ID="FGrID1" USE="archive"><mets:file ID="FID1" ADMID="file_1" MIMETYPE="application/pdf" USE="maitre"><mets:FLocat LOCTYPE="URL" xlink:href="https://ged.univ-rennes1.fr/nuxeo/site/esupversions/22c0a665-0da9-475e-ac17-264b5771e4fd"/></mets:file></mets:fileGrp>
 </mets:fileSec>
    <mets:structMap TYPE="logical">
        <mets:div DMDID="desc_expr" ADMID="dr_expr_thesard dr_expr_univ admin_expr" TYPE="THESE" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-21588/oeuvre">
            <mets:div ADMID="dr_version" TYPE="VERSION_COMPLETE" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-21588/oeuvre/version">
                <mets:div DMDID="desc_edition" TYPE="EDITION" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-21588/oeuvre/version/edition">
                    <mets:fptr FILEID="FGrID1"/>
                </mets:div>
            </mets:div>
        </mets:div>
    </mets:structMap>
</mets:mets>