Perceptual rhythm determination of music signal for emotion-based classification

Abstract

Music information retrieval (MIR) systems able to classify and retrieve different emotional expression in music pieces are still in its infancy. The challenge is on automatically extracting the perceptual features from music signal. Three rhythmic features that have influence on perceived emotional expression in music are: the tempo (fast/slow), the articulation (staccato/legato) and the motion (firm/flowing, where firm event is mainly evoked by the variation of loudness among events or by the durational variation between events). So far, only parts of the rhythmic features were extracted and used for emotion classification. As a result, either the classification result was not satisfactory or only broad classification of emotion was achieved. In this paper, we propose efficient and effective algorithms to determine these three rhythmic features based on both the findings from music psychology and psycho acoustics researches. Experimental results, with polyphonic music extracts mainly from CD recordings, have shown that our proposed algorithms are effective in determining these three rhythmic features