Identifying repeated patterns in music using sparse convolutive non-negative matrix factorization

We describe an unsupervised, data-driven, method for automatically identifying repeated patterns in music by analyzing a feature matrix using a variant of sparse convolutive non-negative matrix factorization. We utilize sparsity constraints to automatically identify the number of patterns and their lengths, parameters that would normally need to be fixed in advance. The proposed analysis is applied to beatsynchronous chromagrams in order to concurrently extract repeated harmonic motifs and their locations within a song. Finally, we show how this analysis can be used for longterm structure segmentation, resulting in an algorithm that is competitive with other state-of-the-art segmentation algorithms based on hidden Markov models and self similarity matrices.