Mirex 2012 Audio Beat Tracking Evaluation: Beat.e

In this paper, we present a Hidden Markov Model (HMM) based beat tracking system that simultaneously extracts downbeats, beat times, tempo, meter and rhythmic patterns. Our model builds upon the basic structure proposed by Whiteley et. al [9], which we further modified by introducing a new observation model: rhythmic patterns are learned directly from data, which makes the model adaptable to the rhythmical structure of any kind of music. The MIREX beat tracking evaluation 30 results using ten measures and three datasets placed our algorithm among the top three performing algorithms thirteen times and always inside the top ten.