The Journal of the Acoustical Society of Korea (한국음향학회지)

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

DOI QR Code

A Musical Genre Classification Method Based on the Octave-Band Order Statistics

옥타브밴드 순서 통계량에 기반한 음악 장르 분류

  • Seo, Jin Soo (Department of Electronic Engineering, Gangneung-Wonju National University)
  • Received : 2013.10.04
  • Accepted : 2013.11.20
  • Published : 2014.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a study on the effectiveness of using the spectral and the temporal octave-band order statistics for musical genre classification. In order to represent the relative disposition of the harmonic and non-harmonic components, we utilize the octave-band order statistics of power spectral distribution. Experiments on the widely used two music datasets were performed; the results show that the octave-band order statistics improve genre classification accuracy by 2.61 % for one dataset and 8.9 % for another dataset compared with the mel-frequency cepstral coefficients and the octave-band spectral contrast. Experimental results show that the octave-band order statistics are promising for musical genre classification.

본 논문은 음악신호의 옥타브 밴드 상에서 주파수와 시간 방향의 순서 통계량에 기반한 음악분류기에 대한 연구이다. 음악의 화음 및 강약 구조를 표현하기 위해서 파워스펙트럼의 옥타브 밴드 순서 통계량을 이용하였다. 널리 사용되고 있는 두 음악 데이터셋을 이용한 성능 실험을 통해서, 옥타브 밴드 순서 통계량이 기존의 MFCC 와 옥타브밴드 스펙트럼 고저차 특징에 비해서 두 데이터셋에대해 각각 2.61 %와 8.9 % 장르 분류정확도가 개선되었다. 실험결과는 옥타브 밴드 순서 통계량이 음악 장르 분류에 적합함을 보인다.

Keywords

References

  1. G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," IEEE Trans. Speech and Audio Process. 10, 293-302 (2002). https://doi.org/10.1109/TSA.2002.800560
  2. Y. Panagakis, C. Kotropoulos, and G. Arce, "Non-negative multilinear principal component analysis of auditory temporal modulations for music genre classification," IEEE Trans. Audio Speech Lang. Process. 18, 576-588 (2010). https://doi.org/10.1109/TASL.2009.2036813
  3. S.-C. Lim, S.-J. Jang, S.-P. Lee, and M. Y. Kim, "Music genre classification system using decorrelated filter bank," (in Korean) J. Acoust. Soc. Kr. 30, 100-106 (2011). https://doi.org/10.7776/ASK.2011.30.2.100
  4. A. Meng, P. Ahrendt, J. Larsen, and L. Hansen, "Temporal feature integration for music genre classification," IEEE Trans. Audio Speech Lang. Process. 15, 1654 - 1664 (2007). https://doi.org/10.1109/TASL.2007.899293
  5. E. Pampalk, A. Flexer, and G. Widmer, "Improvements of audio-based music similarity and genre classification," in Proc. ISMIR-2005, 634-637 (2005).
  6. D. Jiang, L. Lu, H. Zhang, J. Tao, and L. Cai, "Music type classification by spectral contrast feature," in Proc. ICME-2002, 113-116 (2002).
  7. P. Loizou and O. Poroy, "Minimum spectral contrast needed for vowel identification by normal-hearing and cochlear implant listeners," J. Acoust. Soc. Am. 110, 1619-1627 (2001). https://doi.org/10.1121/1.1388004
  8. J. Seo and S. Lee, "Higher-order moments for musical genre classification," Signal Processing 91, 2154-2157 (2011). https://doi.org/10.1016/j.sigpro.2011.03.019
  9. S.-C. Lim, J.-S. Lee, S.-J. Jang, S.-P. Lee, and M. Kim, "Music-genre classification system based on spectro-temporal features and feature selection," IEEE Trans. Consum. Electron. 58, 1262-1268 (2012). https://doi.org/10.1109/TCE.2012.6414994

Cited by

  1. Centroid-model based music similarity with alpha divergence vol.35, pp.2, 2016, https://doi.org/10.7776/ASK.2016.35.2.083