The “groove” of a song correlates with enjoyment and bodily movement. Recent work has shown that humans often agree whether a song does or does not have groove and how much groove a song has. It is therefore useful to develop algorithms that characterize the quality of groove across songs. We evaluate three unsupervised tempo-invariant models for measuring pairwise musical groove similarity: A temporal model, a timbre-temporal model, and a pitch-timbre-temporal model. The temporal model uses a rhythm similarity metric proposed by Holzapfel and Stylianou, while the timbre-inclusive models are built on shift invariant probabilistic latent component analysis. We evaluate the models using a dataset of over 8000 real-world musical recordings spanning approximately 10 genres, several decades, multiple meters, a large range of tempos, and Western and non-Western localities. A blind perceptual study is conducted: given a random music query, humans rate the groove similarity of the top three retrievals chosen by each of the models, as well as three random retrievals.
More info can be found at (Sarroff & Casey, 2013).
- Sarroff, A. M., & Casey, M. (2013). Groove kernels as rhythmic-acoustic motif descriptors. In Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR) (p. 299—304). Link. Details