Computational Model for Automatic Chord Voicing based on Bayesian Network
Tetsuro Kitahara, Makiko Katsura, Haruhiro Katayose, Noriko Nagata · 2008
We developed a computational model for automatically voicing chords based on a Bayesian network. Automatic chord voicing is difficult because it is necessary to choose extended notes and inversions by taking into account musical simultaneity and sequentiality. We overcome this difficulty by inferring the most likely chord voicing using a Bayesian network model where musical simultaneity and sequeniality are modeled as probabilistic dependencies between nodes. The model represents musical simultaneity as probabilistic dependencies between voicing and melody nodes while it represents musical sequentiality as probabilistic dependencies between currentchord and previous- or following-chord voiding nodes. The model makes it possible to take into account both simultaneity and sequentiality at a single inference process. Experimental results of chord voicing for jazz musical pieces showed that our system generated chord voicings that had appropriate simultaneity and sequentiality.