A Cross-version Approach for Stabilizing Tempo-based Novelty Detection

The task of novelty detection with the objective of detecting changes regarding musical properties such as harmony, dynamics, timbre, or tempo is of fundamental importance when analyzing structural properties of music recordings. But for a specific audio version of a given piece of music, the novelty detection result may also crucially depend on the individual performance style of the musician. This particularly holds true for tempo-related properties, which may vary significantly across different performances of the same piece of music. In this paper, we show that tempobased novelty detection can be stabilized and improved by simultaneously analyzing a set of different performances. We first warp the version-dependent novelty curves onto a common musical time axis, and then combine the individual curves to produce a single fusion curve. Our hypothesis is that musically relevant points of novelty tend to be consistent across different performances. This hypothesis is supported by our experiments in the context of music structure analysis, where the cross-version fusion curves yield, on average, better results than the novelty curves obtained from individual recordings.