Sciweavers

Share
ISMIR
2005
Springer

A Probabilistic Model for Chord Progressions

9 years 9 months ago
A Probabilistic Model for Chord Progressions
Chord progressions are the building blocks from which tonal music is constructed. Inferring chord progressions is thus an essential step towards modeling long term dependencies in music. In this paper, a distributed representation for chords is designed such that Euclidean distances roughly correspond to psychoacoustic dissimilarities. Estimated probabilities of chord substitutions are derived from this representation and are used to introduce smoothing in graphical models observing chord progressions. Parameters in the graphical models are learnt with the EM algorithm and the classical Junction Tree algorithm is used for inference. Various model architectures are compared in terms of conditional out-of-sample likelihood. Both perceptual and statistical evidence show that binary trees related to meter are well suited to capture chord dependencies.
Jean-François Paiement, Douglas Eck, Samy B
Added 27 Jun 2010
Updated 27 Jun 2010
Type Conference
Year 2005
Where ISMIR
Authors Jean-François Paiement, Douglas Eck, Samy Bengio
Comments (0)
books