Modeling rhythm similarity for Electronic Dance Music

A model for rhythm similarity in electronic dance music (EDM) is presented in this paper. Rhythm in EDM is built on the concept of a ‘loop’, a repeating sequence typically associated with a four-measure percussive pattern. The presented model calculates rhythm similarity between segments of EDM in the following steps. 1) Each segment is split in different perceptual rhythmic streams. 2) Each stream is characterized by a number of attributes, most notably: attack phase of onsets, periodicity of rhythmic elements, and metrical distribution. 3) These attributes are
combined into one feature vector for every segment, after which the similarity between segments can be calculated. The stages of stream splitting, onset detection and downbeat detection have been evaluated individually, and a listening experiment was conducted to evaluate the overall performance of the model with perceptual ratings of rhythm similarity.