Music emotions recognition by cognitive classification methodologies

Abstract

Music emotions recognition (MER) is a challenging field of studies addressed in multiple disciplines such as musicology, cognitive science, physiology, psychology, arts and affective computing. In this paper, music emotions are classified into four types known as those of pleasing, angry, sad and relaxing. MER is formulated as a classification problem in cognitive computing where 548 dimensions of music features are extracted and modeled. A comprehensive set of classification algorithms are explored and comparatively studied for MER including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Neuro-Fuzzy Networks Classification (NFNC), Fuzzy KNN (FKNN), Bayes classifier and Linear Discriminant Analysis (LDA). Experimental results show that the SVM, FKNN and LDA algorithms are the most effective methodologies which obtain more than 80% accuracy for MER in performance.