Sparse coding methods for music induced emotion recognition

Abstract

The paper concerns automatic recognition of emotion induced by music (MER, Music Emotion Recognition). Comparison of different sparse coding schemes in a task of MER is the main contribution of the paper. We consider a domain-specific categorization of emotions, called Geneva Emotional Music Scale (GEMS), which focuses on induced emotions rather than expressed emotions. We were able to find only one dataset, namely Emotify, in which data are annotated with GEMS categories, this set was used in our experiments. Our main goal was to compare different sparse coding approaches in a task of learning features useful for predicting musically induced emotions, taking into account categories present in the GEMS. We compared five sparse coding methods and concluded that sparse autoencoders outperform other approaches.