Probabilistic Models for Music

This website contains additional material related to the PhD thesis entitled Probabilistic Models for Music, by J.-F. Paiement (École Polytechnique Fédérale de Lausanne, 2008.)


This thesis proposes to analyze 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:

Keywords: Machine learning, music, probabilistic models, generative models, chord progressions, melodies.
Last modified: Thu May 29 16:35:36 CEST 2008