Browse > Article

Music Genre Classification based on Musical Features of Representative Segments  

Lee, Jong-In (금오공과대학교 소프트웨어공학)
Kim, Byeong-Man (금오공과대학교 컴퓨터공학부)
Abstract
In some previous works on musical genre classification, human experts specify segments of a song for extracting musical features. Although this approach might contribute to performance enhancement, it requires manual intervention and thus can not be easily applied to new incoming songs. To extract musical features without the manual intervention, most of recent researches on music genre classification extract features from a pre-determined part of a song (for example, 30 seconds after initial 30 seconds), which may cause loss of accuracy. In this paper, in order to alleviate the accuracy problem, we propose a new method, which extracts features from representative segments (or main theme part) identified by structure analysis of music piece. The proposed method detects segments with repeated melody in a song and selects representative ones among them by considering their positions and energies. Experimental results show that the proposed method significantly improve the accuracy compared to the approach using a pre-determined part.
Keywords
Music Genre Classification System; Music Representative Part Detection; Musical Structure Analysis; Music Segment Detection; Content-based Music Feature Extraction;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Tzanetakis, G. and Cook, P., "Musical genre classification of audio signals," Speech and Audio Processing, IEEE Transactions on Vol. 10, No. 5, pp. 293-302, 2002   DOI   ScienceOn
2 Jiang, D., Lu, L., Zhang, H., Tao, J. and Cai, L., "Music type classification by spectral contrast feature," Proc. of ICME `02, Vol. 1, pp. 113-116, 2002
3 DeCoro, C., Barutcuoglu, Z., and Fiebrink, R., "Bayesian Aggregation for Hierarchical Genre Classification," Proc. of International Symposium on Music Information Retrieval 2007, 2007
4 Shao, X., Maddage, N.C., Xu, C. and Kankanhalli, M.S., "Automatic music summarization based on music structure analysis," Proc. of ICASSP'05, Vol. 2, pp. 1169-1172, 2005
5 Shiu, Y., Jeong, H. and Kuo, C.-C. J., "Musical structure analysis using similarity matrix and dynamic programming," Proc. of SPIE, Multimedia systems and applications, Vol. 3, pp. 398-409, 2005
6 Lu, L. and Zhang, H., "Automated extraction of music snippets," Proc. of the 11'th ACM inter- national conference on Multimedia, pp. 140-147, 2003
7 Burred, J. J. and Lerch, A., "A Hierarchical Approach to automatic Musical Genre Classification," Proc. of the 6th Int. Conference on Digital Audio Effects (DAFx-03), 2003
8 Paulus, J. and Klapuri, A., "Music Structure Analysis by Finding Repeated Parts," Proc. of ACM AMCMM'06, pp. 59-67, 2006
9 Aucouturier, J.-J. and Pachet, F., "Representing musical genre: A state of the art," Journal of new musical research, Vol. 32, No. 1, pp. 83-93, 2003   DOI   ScienceOn
10 http://en.wikipedia.org/wiki/Pitch_class
11 Goto, M., "SmartMusicKIOSK: music listening station with chorus-search function," Proc. of the 16th annual ACM symposium on User interface software and technology, pp. 31-40, 2003
12 Kim, Y. K. and Brian, Y., "Singer Identification in Popular Music Recordings Using Voice Coding Features," Proc. of Int'l Conf. on Music Information Retrieval, 2002
13 Li, T. and Ogihara, M., "Music genre classification with taxonomy," Proc. of ICASSP '05, Vol. 5, pp. 197-200, March 2005
14 Zhang, T. and Samadani, R., "Automatic Generation of Music Thumbnails," Proc. of IEEE International Conference on Multimedia and Expo, pp. 228-231, 2007
15 Zhang, T., "Automatic Singer Identification," Proc. of IEEE Int'l Conf. on Multimedia and Expo, IEEE CS Press, 2003
16 Li, T., Ogihara, M. and Li, Q., "A comparative study on content-based music genre classification," Proc. of the 26th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 282-289, 2003