Automatic Musical Genre Classification Using Divergence and Average Information Measures

Recently many research has been conducted to retrieve pertinent parameters and adequate models for automatic music genre classification. In this paper, two measures based upon information theory concepts are investigated for mapping the features space to decision space. A Gaussian Mixture Model (GMM) is used as a baseline and reference system. Various strategies are proposed for training and testing sessions with matched or mismatched conditions, long training and long testing, long training and short testing. For all experiments, the file sections used for testing are never been used during training. With matched conditions all examined measures yield the best and similar scores (almost 100%). With mismatched conditions, the proposed measures yield better scores than the GMM baseline system, especially for the short testing case. It is also observed that the average discrimination information measure is most appropriate for music category classifications and on the other hand the divergence measure is more suitable for music subcategory classifications.

Authors:

• Hassan Ezzaidi
• Jean Rouat

Keywords:

• Audio feature
• information measures
• music genre.

References:

[1] H. Ezzaidi and J. Rouat, Speech, music and songs discrimination in the
context of handsets variability, In proceedings of ICSLP 2002, 16-20
September 2002.
[2] FT. Lambrou, P. Kudumakis, M. Sandler, R. Speller and A. Linney,
Classification of Audio Signals using Statistical Features on Time and
Wavelet Transform Domains, In IEEE ICASSP 98, May 1998, Seattle,
USA.
[3] J. Tou and R. Gonzalez. Pattern recognition principles, Addison-Wesley
Publishinig Company, Reading, Massachusetts , 1974.
[4] Masataka Goto, Hiroki Hashiguchi, Takuichi Nishimura, and Ryuichi
Oka,RWC Music Database: Music Genre Database and Musical
Instrument Sound Database, In Proceedings of the 4th International
Conference on Music Information Retrieval (ISMIR 2003), pp. 229-230,
October 2003.
[5] Aucouturier, J.J and Pachet, F. Musical Genre: a Survey. In Journal of
New Music Research, Vol. 32, No 1, pp.83- 93, 2003.
[6] Ricardo Malheiro, Rui P. Paiva, Ant ˆ Unio Mendes, Teresa Mendes,
Amilcar Cardoso, A Prototype for Classification of Classical Music
using Neural Networks, In Proc. of the 8th IASTED International
Conference on Artificial Intelligence and Soft Computing, pp. 294-299,
ASC-2004, Marbella, Spain, September-2004.
[7] H. Soltau, T. Schultz, M. Westphal, and A. Waibel. Recognition of
Musical Types. In Proceedings International Conference on Acoustics,
Speech and Signal Processing (ICASSP)., May 1998, vol. 2, pp.
1137˜n1140.
[8] Tzanetakis, G., Essl, G., and Cook, P., Automatic Musical Genre
Classification of Audio Signals, In Proceedings of the 2001
International Symposium on Music Information Retrieval, 2001.
[9] Tzanetakis, G., and P. R. Cook, Musical Genre Classification of Audio
Signals, In IEEE Transactions on Speech and Audio, July, 2002.
[10] Li, Tao and Tzanetakis, George, Factors in Automatic Musical Genre
Classification of Audio Signals, In Proc. IEEE Workshop on
Applications of Signal Processing to Audio and Acoustics (WASPAA),
New Paltz, NY October 2003.
[11] Tao Li, Mitsunori Ogihara, and Qi Li. A Comparative Study on Content-
Based Music Genre Classification, In Proceedings of Annual ACM
Conference on Research and Development in Information Retrieval, (
SIGIR 2003),Pages 282-289.
[12] Douglas Turnbull, Charles Elkan, Fast Recognition of Musical Genres
Using RBF Networks, In IEEE Trans. Knowl. Data Eng, 17(4): 580-584
(2005).