The analysis of mood taxonomy comparision between chinese and western music

Abstract

Automatic discrimination of music mood is one important field of MIR. Considering the difference of Chinese traditional music and Western classical music, it is necessary to study these two kinds of music's mood taxonomy. In this paper, the mood taxonomy models of Chinese traditional music and Western classical music are implemented, and then three content feature sets are extracted directly from the waveform audio clips. Finally, music clips are classified by three feature sets and their combination using Bayesian network classifier. The experiment results indicate that the detection rate of Chinese traditional music mood taxonomy is lower than that of Western classical music mood taxonomy no matter using single feature set or their combinations, that is to say the contribution of different feature set to music mood taxonomy is different, and the detection rate improves obviously when combining three feature sets both for Chinese traditional music and Western classical music.