000124848 001__ 124848
000124848 005__ 20190619003137.0
000124848 0247_ $$2doi$$a10.5075/epfl-thesis-4148
000124848 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis4148-5
000124848 02471 $$2nebis$$a5578911
000124848 037__ $$aTHESIS
000124848 041__ $$aeng
000124848 088__ $$a4148
000124848 245__ $$aProbabilistic models for music
000124848 269__ $$a2008
000124848 260__ $$bEPFL$$c2008$$aLausanne
000124848 300__ $$a128
000124848 336__ $$aTheses
000124848 520__ $$aThis thesis proposes to analyse symbolic musical data under a statistical viewpoint, using state-of-the-art machine learning techniques. Our main argument is to show that it is possible to design generative models that are able to predict and to generate music given arbitrary contexts in a genre similar to a training corpus, using a minimal amount of data. For instance, a carefully designed generative model could guess what would be a good accompaniment for a given melody. Conversely, we propose generative models in this thesis that can be sampled to generate realistic melodies given harmonic context. Most computer music research has been devoted so far to the direct modeling of audio data. However, most of the music models today do not consider the musical structure at all. We argue that reliable symbolic music models such a the ones presented in this thesis could dramatically improve the performance of audio algorithms applied in more general contexts. Hence, our main contributions in this thesis are three-fold: We have shown empirically that long term dependencies are present in music data and we provide quantitative measures of such dependencies; We have shown empirically that using domain knowledge allows to capture long term dependencies in music signal better than with standard statistical models for temporal data. We describe many probabilistic models aimed to capture various aspects of symbolic polyphonic music. Such models can be used for music prediction. Moreover, these models can be sampled to generate realistic music sequences; We designed various representations for music that could be used as observations by the proposed probabilistic models.
000124848 6531_ $$amachine learning
000124848 6531_ $$amusic
000124848 6531_ $$aprobabilistic models
000124848 6531_ $$agenerative models
000124848 6531_ $$achord progressions
000124848 6531_ $$amelodies
000124848 6531_ $$aapprentissage machine
000124848 6531_ $$amusique
000124848 6531_ $$amodèles probabilistes
000124848 6531_ $$amodèles génératifs
000124848 6531_ $$aprogressions d'accords
000124848 6531_ $$amélodies
000124848 700__ $$aPaiement, Jean-François
000124848 720_2 $$aBourlard, Hervé$$edir.$$g117014$$0243348
000124848 720_2 $$aBengio, Samy$$edir.$$g140142$$0243961
000124848 8564_ $$uhttps://infoscience.epfl.ch/record/124848/files/EPFL_TH4148.pdf$$zTexte intégral / Full text$$s1449118$$yTexte intégral / Full text
000124848 909C0 $$xU10381$$0252189$$pLIDIAP
000124848 909CO $$pthesis-bn2018$$pthesis-public$$pDOI$$ooai:infoscience.tind.io:124848$$qGLOBAL_SET$$pSTI$$qDOI2$$pthesis
000124848 917Z8 $$x108898
000124848 918__ $$cIEL$$aSTI
000124848 919__ $$aLIDIAP
000124848 920__ $$b2008
000124848 970__ $$a4148/THESES
000124848 973__ $$sPUBLISHED$$aEPFL
000124848 980__ $$aTHESIS