Sequential Complexity as a Descriptor for Musical Similarity∗

We propose string compressibility as a descriptor of temporal struc-ture in audio, for the purpose of determining musical similarity. Our descriptors are based on computing track-wise compression rates of quan-tised audio features, using multiple temporal resolutions and quantisation granularities. To verify that our descriptors capture musically relevant information, we incorporate our descriptors into similarity rating prediction and song year prediction tasks. We base our evaluation on a dataset of 15 500 track excerpts of Western popular music, for which we obtain 7 800 web-sourced pairwise similarity ratings. To assess the agreement among similarity rat-ings, we perform an evaluation under controlled conditions, obtaining a rank correlation of 0.33 between intersected sets of ratings. Combined with bag-of-features descriptors, we obtain performance gains of 18.5% and 9.9 % for similarity rating prediction and song year prediction. For both tasks, analysis of selected descriptors reveals that representing fea-tures at multiple time scales benefits prediction accuracy.