The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Music Genre Classification System Using Decorrelated Filter Bank

Decorrelated Filter Bank를 이용한 음악 장르 분류 시스템

  • 임신철 (세종대학교 정보통신공학과) ;
  • 장세진 (전자부품연구원 디지털미디어연구센터) ;
  • 이석필 (전자부품연구원 디지털미디어연구센터) ;
  • 김무영 (세종대학교 정보통신공학과)
  • Received : 2011.01.30
  • Accepted : 2011.02.16
  • Published : 2011.02.28
Download PDF
⟨ Previous Next ⟩

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.

음원의 디지털화가 진행되면서 음악 데이터베이스가 방대해지고 있다. 따라서, 음악 데이터를 보다 효과적으로 관리하기 위해 음악의 특성에 따라 장르별로 자동 분류해주는 시스템이 필요하다. 기존 장르 분류 시스템은 대부분 Mel-Frequency Cepstral Coefficient (MFCC)를 특징 벡터로 이용하고 있다. 본 논문에서는 Auditory Filter Bank를 이용한 Decorrelated Filter Bank (DFB)와 Octave-based Spectral Contrast (OSC)에 texture window를 적용하여 특징을 추출한 후, Support Vector Machine (SVM)을 이용하여 장르 분류를 시도하였다. 기존의 Marsyas 장르 분류 시스템과 비교한 결과 DFB와 OSC로 복합적인 특징 벡터를 구성하면 더 적은 차수의 특징벡터를 사용함에도 4.2 %의 향상된 분류 성공률을 얻을 수 있었다.

Keywords

References

  1. N. Scaringella, G. Zoia, and D. Mlynek, "Automatic genre classification of music content: A survey," IEEE Signal Process., vol. 23, no. 2, pp. 133-141, 2006.
  2. J. Foote, "Content-based retrieval of music and audio," in Proc. SPIE Multimedia Storage Archiving Systems II, vol. 3229, pp. 138-147, 1997.
  3. U. Bagci and E. Erzin, "Automatic Classification of musical Genres using Inter-genre Similarity," IEEE Signal process. Letters, vol. 14, no 8, pp. 521-424, 2007. https://doi.org/10.1109/LSP.2006.891320
  4. G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," IEEE Trans. Speech Audio Process., vol. 10, no. 5, pp. 293-302, 2002. https://doi.org/10.1109/TSA.2002.800560
  5. D. N. Jiang, L. Lu, H. J. Zhang, J. H. Tao, and L. H. Cai, "Music type classification by spectral contrast feature," in Proc. IEEE Int. Conf. Multimedia and Expo, vol. 1, pp. 113- 116, 2002.
  6. Y. Zhang and J. Zhou, "A study on content-based music classification," in Proc. Signal Process. and Its applications, vol. 2, pp. 113-116, 2003.
  7. S. Z. Li, "Content-based classification and retrieval audio using the nearest feature line method," IEEE Trans. Speech and Audio Process., vol. 8, no. 5, pp. 619-625, 2000. https://doi.org/10.1109/89.861383
  8. C. Xu, N. C. Maddage, and X, Shao, "Automatic music classification and summarization," IEEE Trans. Speech and Audio Process., vol. 13, no. 3, pp. 441-450, 2005. https://doi.org/10.1109/TSA.2004.840939
  9. 박철의, 박만수, 김성탁, 김회린, "피치 히스토그램과 MFCC-VQ 동적 패턴을 사용한 음악검색," 한국음향학회지, 24권, 3호, 178-185쪽, 2005.
  10. J. Ming, T. J. Hazen, J. R. Glass, and D. A. Reynolds, "Robust speaker recognition in noisy conditions," IEEE Trans. Audio, Speech, Language Process., vol. 15, no. 5, pp. 1711-1723, 2007. https://doi.org/10.1109/TASL.2007.899278
  11. J. Jung, K. Kim, and M. Y. Kim, "Noise robust speaker identification based on the advanced missing feature theory," Electronics Letters, vol. 46, no. 14, pp. 1027-1029, 2010. https://doi.org/10.1049/el.2010.0368
  12. Y. Wang, "A Tree-Based Multi-class SVM Classifier for Digital Library Document," in Proc. IEEE Int. Conf. Multimedia and Information Technology, pp. 15-18, 2008.
  13. 한학용, "패턴인식 개론 : MATLAB 실습을 통한 입체적 학습," 2005.
  14. GTZAN Genre Collection Database, "http://marsyas.info/download/data_sets"
  15. G. Tzanetakis, "MARSYAS SUBMISSIONS TO MIREX 2009," Music Information Retrieval Evaluation eXchange (MIREX), 2009.

Cited by

  1. Combining visual and acoustic features for music genre classification vol.45, 2016, https://doi.org/10.1016/j.eswa.2015.09.018
  2. A Musical Genre Classification Method Based on the Octave-Band Order Statistics vol.33, pp.1, 2014, https://doi.org/10.7776/ASK.2014.33.1.081
  3. Music-genre classification system based on spectro-temporal features and feature selection vol.58, pp.4, 2012, https://doi.org/10.1109/TCE.2012.6414994