An adaptive learning approach to music tempo and beat analysis

In beat tracking, a listener's experience of the tempo from a previous excerpt of a music piece is usually a good prediction of the tempo of the following excerpt in the same piece of music. A human being has this ability to adjust adaptively his or her tap to synchronize with the tempo of music. An adaptive learning approach, based on maximum a posteriori (MAP) estimation, is proposed to integrate the propagated knowledge from the previous excerpt and to infer the tempo. Our experiments on real musical signals show that: (1) the extracted tempo and beat using MAP are more robust and less sensitive to the window size of the analysis; (2) the adaptive framework facilitates easy fusion, using results and knowledge from different analysis schemes.