Empirical Research on a Fuzzy Model of Music Emotion Classification Based on Pleasure-Arousal Model

Affective computing plays a key role in music artificial intelligence, in which a music emotion classification model is indispensable. Both discrete classification model and continuous dimensional model are commonly used for music emotion classification. However, these models are not designed in views of composers, which is insufficient for the perception of music emotion. In this paper, a fuzzy music emotion classification model is proposed by extracting the music expression marks considering the composers emotion. Experiments on subjective evaluation in the feeling of pleasure and arousal according to the change of three selected features (i.e., tempo, register, and dynamic) are conducted by listeners from different subjects. The experimental results show that the correlation between the proposal fuzzy model and the the results from questionnaires reaches 80% on average, which demonstrate the validity of the proposed fuzzy music emotion classification model. The proposal could be applied to music emotion generation conveyed from either composers or players, and to emotion recognition of music as for audiences.