Sciweavers

ICML
2005
IEEE

A graphical model for chord progressions embedded in a psychoacoustic space

14 years 4 months ago
A graphical model for chord progressions embedded in a psychoacoustic space
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. Parameters in the graphical models are learnt with the EM algorithm and the classical Junction Tree algorithm. Various model architectures are compared in terms of conditional outof-sample likelihood. Both perceptual and statistical evidence show that binary trees related to meter are well suited to capture chord dependencies.
David Barber, Douglas Eck, Jean-François Pa
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2005
Where ICML
Authors David Barber, Douglas Eck, Jean-François Paiement, Samy Bengio
Comments (0)