A Consumer BCI for Automated Music Evaluation With

Authors: Fotis Kalaganis Dimitrios A Adamos Nikos Laskaris

Publish Date: 2016/9/16

Volume: , Issue: , Pages: 429-440

PDF Link

Abstract

We investigated the possibility of a using a machinelearning scheme in conjunction with commercial wearable EEGdevices for translating listener’s subjective experience of music into scores that can be used for the automated annotation of music in popular ondemand streaming servicesBased on the established neuroscientifically sound concepts of brainwave frequency bands activation asymmetry index and crossfrequencycoupling CFC we introduce a Brain Computer Interface BCI system that automatically assigns a rating score to the listened songOur research operated in two distinct stages i a generic feature engineering stage in which features from signalanalytics were ranked and selected based on their ability to associate music induced perturbations in brainwaves with listener’s appraisal of music ii a personalization stage during which the efficiency of extreme learning machines ELMs is exploited so as to translate the derived patterns into a listener’s score Encouraging experimental results from a pragmatic use of the system are presented

Keywords: