Automatic Music Genre Classification Using Modulation Spectral Features and Nonparametric Discriminant Analysis

10.6302/JITA.201106_5(2).0003

Chang-Hsing Lee；Chih-Hsun Chou；Jen-Cheng Fang

Mel-frequency cepstral coefficients ； modulation spectral analysis ； music genre classification ； normalized audio spectrum envelope ； octave-based spectral contrast

Journal of Information Technology and Applications(資訊科技與應用期刊)

5卷2期（2011 / 06 / 01）

75 - 82

英文

In this paper, we will propose an automatic music genre classification approach based on long-term modulation spectral analysis of spectral (OSC and MPEG-7 NASE) as well as cepstral (MFCC) features. Modulation spectral analysis of every feature value will generate a corresponding modulation spectrum and all the modulation spectra can be collected to form a modulation spectrogram which exhibits the time-varying or rhythmic information of music signals. Each modulation spectrum is then decomposed into several logarithmically-spaced modulation subbands. A new set of modulation spectral features, including modulation spectral contrast (MSC), modulation spectral valley (MSV), modulation spectral energy (MSE), modulation spectral centroid (MSCEN) and modulation spectral flatness (MSF) are then computed from each modulation subband. Effective and compact features are generated from statistical aggregations of the MSC, MSV, MSE, MSCEN, and MSF features of all modulation subbands. An information fusion approach which integrates both feature level fusion method and decision level combination method is then employed to improve the classification accuracy. Experiments conducted on ISMIR 2004 music dataset have shown that our proposed approach can achieve higher classification accuracy than other approaches with the same experimental setup.

1. 吳思(2016)。一個基於AHP權重的兩步驟式音樂分類演算法。交通大學資訊管理研究所學位論文。2016。1-37。