Abstract
This paper presents a process for determining the music genre of an item using a new set of descriptors. A discrete wavelet packet transform is applied to obtain the signal representation at two different resolutions: a frequency resolution and a time resolution tuned to encode music notes and their onset and offset. These features are tested on a number of data sets as descriptors for music genre classification. Lazy learning classifiers (k-nearest neighbor) and eager learners (neural networks and support vector machines) are applied in order to assess the classification power of the proposed features. Different feature selection techniques and ensemble methods are explored to maximize the accuracy of the classifiers and stabilize their behavior. Our evaluation shows that these frequency descriptors perform better than a standard approach based on Mel-Frequency Cepstral Coefficients and on the Short Time Fourier Transform in music genre classification. Moreover, our work confirms that a parameterization of the music rhythm based on the beat-histogram provides some meaningful information in the context of music classification by genre.Finally, our evaluation suggests that multi-class support vector machines with a linear kernel and round-robin binarization are the simplest and more effective process for music genre classification.
Similar content being viewed by others
References
Allamanche, E., Herre, J., Hellmuth, O., Froeba, B., Kastner, T., Kremer, M.: Content-based identification of audio material using mpeg-7 low level description. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2001). Bloomington, IN, USA (2001)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm (2001)
Cunningham, P., Carney, J.: Diversity versus quality in classification ensembles based on feature selection. In: Eleventh European Conference on Machine Learning (ECML 2000). pp. 109–116 Springer-Verlag, Berlin (2000)
Daubechies, I.: Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics, Philadelphia, PA, USA (1992)
Dietterich, T.G.: Ensemble methods in machine learning. Lect. Notes Comput. Sci. 1857, 1–15 (2000)
Dixon, E.P., Widmer, G.: Classification of dance music by periodicity patterns. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2003). Baltimore, MA, USA (2003)
Fausett, L.: Fundamentals of Neural Networks: Architecture, Algorithms and Applications. Prentice-Hall, Englewood Cliffs (1994)
Foote, T.: Content-based retrieval of music and audio. In: Multimedia Storage and Archiving Systems II, Proceedings of the SPIE, vol. 3229, pp. 138–147 (1997)
Foote, J.: Arthur: retrieving orchestral music by long term structure. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2000). Plymouth, MA, USA, (2000)
Fürnkranz, J.: Round robin rule learning. In: ICML '01: Proceedings of the Eighteenth International Conference on Machine Learning. pp. 146–153. San Francisco, CA, USA, Morgan Kaufmann (2001)
Grimaldi, M., Cunningham, P., Kokaram, A.: A wavelet packet representation of audio signals for music genre classification using different ensemble and feature selection. In: Proceedings of the 5th ACM SIGMM International Workshop on Multimedia Information Retrieval. Berkeley, CA, USA (2003)
Grimaldi, M.: Learning to Annotate Music Files using Content Based Retrieval Systems and Wavelet Packet Approximations of the Input Signals. PhD thesis, Trinity College Dublin (2004)
Hsu, C.-W., Lin, C.-J.: A comparison of methods for multi-class support vector machines. IEEE Trans. Neural Networks 13(2), 415–425 (2002)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. IEEE Trans. Neural Networks 97(1-2), 273–324 (1997)
Langley, P.: Selection of relevant features in machine learning. In: Proceedings of the AAAI Fall Symposium on Relevance, New Orleans, USA, AAAI Press (1994)
Li, T., Ogihara, M., Li, Q.: A comparative study on content-based music genre classification. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 282–289 (2003)
Logan, B.: Mel frequency cepstral coefficients for music modeling. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2000). Plymouth, MA, USA, 2000
Mallat, S.G.: A Wavelet Tour of Signal Processing. Academic Press, San Diego (1999)
Martin, K.: Musical instrument identification: a pattern-recognition approach. In: The 136th Meeting of the Acoustical Society of America (1998)
Martin, K.D.: Toward automatic sound source recognition: identifying musical instruments. In: Proceedings of the NATO Computational Hearing Advanced Institute. Il Ciocco, Italy (1998)
McKinney, M.F., Breebaart, J.: Features for audio and music classification. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2003). Baltimore, MA, USA (2003)
Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)
Pienimäki, A.: Indexing music databases using automatic extraction of frequent phrases. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR). Paris, France (2002)
Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)
Scheirer, E.D.: Tempo and beat analysis of acoustic musical signals. J. Acouststic Soc. Am. 103(1), 588–601 (1998)
Scheirer, E., Slaney, M.: Construction and evaluation of arobust multifeatures speech/music discriminator. In: IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), vol. 2, pp. 1331–1334. Munich, Germany
Tzanetakis, G., Ermolinskyi, A., Cook, P.: Pitch histograms in audio and symbolic music information retrieval. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR 2002). Paris, France (2002)
Tzanetakis, G., Essl, G., Cook, P.: Automatic musical genre classification of audio signals. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR). Bloomington, IN, USA (2001)
Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)
Wang, Y., Liu, Z., Huang, J.C.: Multimedia content analysis using both audio and visual clues. IEEE Signal Process. Magazine 12–36 (2000)
Zenobi, G., Cunningham, P.: Using diversity in preparing ensemble of classifiers based on different subsets to minimize generalization error. In: 12th European Conference on Machine Leaming (ECML 2001). Springer-Verlag, Berlin (2001)
Zhang, T., Kuo, C.C.: Hierarchical classification of audio data for archiving and retrieving. In: IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP). Phoenix, AZ, USA (1999)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Grimaldi, M., Cunningham, P. & Kokaram, A. Discrete wavelet packet transform and ensembles of lazy and eager learners for music genre classification. Multimedia Systems 11, 422–437 (2006). https://doi.org/10.1007/s00530-006-0027-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-006-0027-z