Identifying "Cover Songs" with Beat-Synchronous Chroma Features

Abstract

Large music collections, ranging from thousands to millions of tracks, are unsuited to manual searching, motivating the development of automatic search methods. When two musical groups perform the same underlying song or piece, these are known as ‘cover’ versions. We describe a system that attempts to identify such a relationship between music audio recordings. To overcome variability in tempo, we use beat-tracking to describe each piece with one feature vector per beat. To deal with variation in instrumentation, we use 12-dimensional chroma feature vectors that collect spectral energy supporting each semitone of the octave. To compare two recordings, we simply cross-correlate the entire beat-by-chroma representation for two tracks and look for sharp peaks indicating good local alignment between the pieces. Evaluation on a small set of 15 pairs of pop music cover versions identified within the USPOP2002 collection achieves a performance of around 60% correct.