Harmonic analysis with probabilistic graphical models

A technique for harmonic analysis is presented that partitions a piece of music into contiguous regions and labels each with the key, mode, and functional chord, e.g. tonic, dominant, etc. The analysis is performed with a hidden Markov model and, as such, is automatically trainable from generic MIDI files and capable of finding the globally optimal harmonic labeling. Experiments are presented highlighting our current state of the art. An extension to a more complex probabilistic graphical model is outlined in which music is modeled as a collection of voices that evolve independently given the harmonic progression.