Music Identification Using brain responses to Initial Snippets

Naturalistic music typically contains repetitive musical pat- terns that are present throughout the song. These patterns form a signature, enabling effortless song recognition. We investigate whether neural responses corresponding to these repetitive patterns also serve as a signature, enabling recogni- tion of later song segments on learning initial segments. We examine EEG encoding of naturalistic musical patterns em- ploying the NMED-T and MUSIN-G datasets. Experiments reveal that (a) training machine learning classifiers on the ini- tial 20s song segment enables accurate prediction of the song from the remaining segments; (b) ? and ? band power spectra achieve optimal song classification, and (c) listener-specific EEG responses are observed for the same stimulus, charac- terizing individual differences in music perception.