Abstract
In this paper we have presented a method for musical genre classification using neural networks. We have used two algorithms (CNN and PRCNN) and two graphical representations: chromograms and spectrograms. We have used a large dataset of music divided into eight genres, with certain overlapping musical features. Key, style-defining elements and the overall character of specific genres are represented in our proposed visual representation and recognized by the networks. We show that the networks have learned to distinguish between genres upon features observable by a human listener and compare the metrics for the network models. Results of the conducted experiments are described and discussed, along with our conclusions and comparison with similar solutions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10, 293–302 (2002)
Sturm, B.L.: A survey of evaluation in music genre recognition. In: Nürnberger, A., Stober, S., Larsen, B., Detyniecki, M. (eds.) AMR 2012. LNCS, vol. 8382, pp. 29–66. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-12093-5_2
Dixon, S., Gouyon, F., Widmer, G.: Towards characterisation of music via rhythmic patterns. In: ISMIR (2004)
Lee, J.-W., Park, S.-B., Kim, S.-K.: Music genre classification using a time-delay neural network. In: Wang, J., Yi, Z., Zurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3972, pp. 178–187. Springer, Heidelberg (2006). https://doi.org/10.1007/11760023_27
Zhouyu, F., Guojun, L., Ting, K., Zhang, D.: A survey of audio-based music classification and annotation. IEEE Trans. Multimedia 13(2), 303–319 (2011)
Bergstra, J., Mandel, M., Eck, D.: Scalable genre and tag prediction with spectral covariance. In: Proceedings of the 11th International Society for Music Information Retrieval Conference, Utrecht, The Netherlands, 9–13 August 2010, pp. 507–512 (2010)
Sturm, B.L.: Classification accuracy is not enough. J. Intell. Inf. Syst. 41(3), 371–406 (2013). https://doi.org/10.1007/s10844-013-0250-y
Jones, D.W.M.: Genre-detectrion with Deep Neural Networks (2019). arXiv preprint
Sturm, B.L.: An analysis of the GTZAN music genre dataset (2012)
Archit Rathore, M.D.: Music Genre Classification (2012). arXiv preprint
Peeters, G., Marchand, U., Fresnel. Q.: GTZAN-Rhythm: extending the GTZAN test-set with beat, downbeat and swing annotations. hal-01252607 (2015)
Guaus, E.: Audio content processing for automatic music genre classification: descriptors, databases, and classifiers. PhD thesis, University Pompeu Fabra, Barcelona, Spain (2009)
Sturm. B.L.: The gtzan dataset: its contents, its faults, their effects on evaluation, and its future use (2013). arXiv preprint arXiv:1306.1461
Free Music Archive. https://freemusicarchive.org
Ellis, D.: Chroma feature analysis and synthesis. Columbia University (2007)
Muller, M.: Chroma toolbox: MATLAB implementations for extracting variants of chroma-based audio features (2011)
Schuller, B., Weninger, F.: Music information retrieval: an inspirational guide to transfer from related disciplines (2012)
Costa, Y., de Oliveira, L.S., Silla, C.: An evaluation of convolutional neural networks for music classification using spectrograms. Appl. Soft Comput. 52, 28–38 (2017)
Krizhevsky, A.: Convolutional Deep Belief Networks on CIFAR-10 (2010)
Warde-Farley, D., Goodfellow, I.J.: Maxout networks (2013)
Zagoruyko, S.: Wide Residual Networks (2016)
Zoph, B.: Neural Architecture Search with Reinforcement Learnings (2017)
Grahams, B.: Fractional Max-Pooling (2015)
Liu, Z., Huang, G.: Densely Connected Convolutional Networks (2018)
Feng, L., Liu, S., Yao, J.: Music genre classification with paralleling recurrent convolutional neural network (2017)
Ghosal, D., Kolekar, M.: Music genre recognition using deep neural networks and transfer learning. In: Interspeech, pp. 2087–2091 (2018)
Panagakis, Y., Kotropoulos, C., Arce, G.: Music genre classification via sparse representations of auditory temporal modulations. In: European Signal Processing Conference (2009)
Panagakis, Y., Kotropoulos, C.: Music genre classification via topology preserving non-negative tensor factorization and sparse representations, pp. 249–252 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Modrzejewski, M., Szachewicz, J., Rokita, P. (2020). Application of Neural Networks and Graphical Representations for Musical Genre Classification. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2020. Lecture Notes in Computer Science(), vol 12415. Springer, Cham. https://doi.org/10.1007/978-3-030-61401-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-61401-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61400-3
Online ISBN: 978-3-030-61401-0
eBook Packages: Computer ScienceComputer Science (R0)