AN ECOLOGICAL APPROACH TO MULTIMODAL SUBJECTIVE MUSIC SIMILARITY PERCEPTION

The perception and cognition of musically similar songs is a well-known research topic in the music information retrieval (MIR) community. There has been much work in the auditive area. More recent approaches investigate the influence of cultural factors on similarity through the use of metadata. Possible bi-modal combinations of audio and cultural facets have been explored recently and we added a third facet, lyrical similarity, to compute tri-modal subjective music similarity. We are interested in an ‘ecological’ approach to validate the perception of musical similarity. This approach takes us out of the lab and into the actual worlds of music users. Being able to observe users’ interactions with music free of experimental manipulation or direction could help us start to build accounts of perception of musical similarity based on cognition ‘in the wild’. These might have important implications both for further understanding of perception of music similarity, and designing the next generation of recommender systems.