A Scheme of MIDI Music Emotion Classification Based on Fuzzy Theme Extraction and Neural Network

摘要

This paper proposes a framework to recognize music emotion, in which an innovative approach to theme extraction is also included. Furthermore, the theme extraction algorithm proposed is based on a fuzzy pattern matching method using a combination of suffix array and dynamic time warping (DTW) algorithm. The classification of music emotion employs an approach of the supervised artificial neural network. Moreover, the output from theme extraction contributes to the input of emotions classification. Experiments are performed, and the results show the efficiency and effectiveness of our scheme.