Off-line refinement of audio-to-score alignment by observation template adaptation

Audio-to-score alignment aims at matching a symbolic representation (the score) to a musical recording. A key problem in this application is the great variability of audio observations which can be explained by a single symbolic element. Whereas most previous works deal with this problem by training or heuristic design of a generic observation model, we propose the adaptation of this model to each musical piece. We exploit a template-based formulation of the observation model and we investigate two strategies for the adaptation of the templates using a Hidden Markov Model for the alignment. Experiments run on a large dataset of popular and classical piano music show that such an approach can lead to a significant improvement of the alignment accuracy compared to the use of a single generic model, even if the latter is trained on real data.