An automatic classification system of the music genres is proposed. Based on the timbre features such as melfrequency cepstral coefficients, the spectro-temporal features are obtained to capture the temporal evolution and variation of the spectral characteristics of the music signal. Mean, variance, minimum, and maximum values of the timbre features are calculated. Modulation spectral flatness, crest, contrast, and valley are estimated for both original spectra and timbre-feature vectors. A support vector machine (SVM) is used as a classifier where an elaborated kernel function is defined. To reduce the computational complexity, an SVM ranker is applied for feature selection. Compared with the best algorithms submitted to the music information retrieval evaluation exchange (MIREX) contests, the proposed method provides higher accuracy at a lower feature dimension for the GTZAN and ISMIR2004 databases 1 .

No abstract

No abstract

No abstract

Music recordings have been digitalized such that huge size of music database is available to the public. Thus, the automatic classification system of music genres is required to effectively manage the growing music database.Mel-Frequency Cepstral Coefficient (MFCC) is a popular feature vector for genre classification. In this paper, the combined super-vector with Decorrelated Filter Bank (DFB) and Octave-based Spectral Contrast (OSC) using texture windows is processed by Support Vector Machine (SVM) for genre classification. Even with the lower order of the feature vector, the proposed super-vector produces 4.2 % improved classification accuracy compared with the conventional Marsyas system.