Automatic music summarization based on temporal, spectral and cepstral features

In this paper, we present an algorithm for automatic music summarization. Spectral power, amplitude envelope and mel-cepstral coefficients are calculated as features to characterize the segmented frames of the music. Based on calculated features, a clustering technique is applied to group segmented frames into different clusters to structure the music content. Finally, the music summary is generated based on the clustering results and domain-specific music knowledge. The proposed algorithm is tested on different genres of music samples and the results of summarization are effective to actual expectation after listening evaluation by experienced users.