A weakly-supervised discriminative model for audio-to-score alignment.

Summary In this paper, we consider a new discriminative approach to the problem of audio-to-score alignment. We consider the two distinct informations provided by the music scores: (i) an exact ordered list of musical events and (ii) an approximate prior information about relative duration of events. We extend the basic dynamic time warping algorithm to a convex problem that learns optimal classifiers for all events while jointly aligning files, using this weak supervision only. We show that the relative duration between events can be easily used as a penalization of our cost function and allows us to drastically improve performances of our approach. We demonstrate the validity of our approach on a large and realistic dataset.