A Mixed Graphical Model for Rhythmic Parsing
This work addresses the problem of automated music analysis for musicians or musicologists, but it appears incremental as it builds on existing graphical model approaches with limited experimental validation.
The paper tackles the rhythmic parsing problem by estimating notated rhythm and tempo from observed musical note onset times using a graphical model that combines discrete rhythm and continuous tempo variables, and demonstrates how to compute the most likely configuration with preliminary experiments on a small dataset.
A method is presented for the rhythmic parsing problem: Given a sequence of observed musical note onset times, we estimate the corresponding notated rhythm and tempo process. A graphical model is developed that represents the simultaneous evolution of tempo and rhythm and relates these hidden quantities to observations. The rhythm variables are discrete and the tempo and observation variables are continuous. We show how to compute the globally most likely configuration of the tempo and rhythm variables given an observation of note onset times. Preliminary experiments are presented on a small data set. A generalization to arbitrary conditional Gaussian distributions is outlined.