Toward Accurate Music Classification Using Local Set-based Multi-label Prototype Selection

  • Authors

    • Wangduk Seo
    • Sanghyun Seo
    • Jaesung Lee
    2018-12-13
    https://doi.org/10.14419/ijet.v7i4.39.23697
  • Auto Music Tags Annotation, Multi-label Learning, Prototype Selection, Pruned Problem Transformation, Local Set-based Smoother

  • Background/Objectives: Multiple music tags enable quick searching and selection of music clips for by end-users to listen to. Our goal is to improve the accuracy of automatic music categorization.

    Methods/Statistical analysis: We propose a local set-based multi-label prototype selection to remove noisy samples in datasets without transforming multi-label datasets to single-label datasets by searching the local set of each sample. To validate the superiority of the proposed method, we use ten multi-label music datasets and Hamming loss as a performance measurement, which counts the symmetric difference between predicted labels and ground truth labels.

    Findings: Considering time and cost, manual categorization of a large collection of music clips is generally impractical. As such, an automated approach for addressing this task through the training of music tags annotated from an online system is employed. In the real world, multiple labels can be annotated to a music clip by users of an online system, resulting in unintended noisy samples due to inaccurate annotations. Conventional methods attempt to transform multi-label datasets to single-label datasets that can yield additional computational cost and unintended removal of non-noisy samples. In this paper, we propose a novel prototype selection method for multi-label music categorization. Experimental results indicate that the proposed method performed the best performance on nine music datasets. From the experiment of CAL500 dataset, multi-label classification performance based on the training samples selected by our proposed method was 0.1402, which indicates that 15,020 labels on average were correctly classified for 100 test samples. Compared to the second-best performance by the compared method, our method was able to classify 245 more labels.

    Improvements/Applications: Experiments using ten different musical datasets showed that the proposed method demonstrated better performance than the compared methods.

     

     

  • References

    1. [1] Chen, S.-Y., Yu, Y., Da, Q., Tan, J., Huang, H.-K., & Tang, H.-H. (2018). Stabilizing reinforcement learning in dynamic environment with application to online recommendation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, pp. 1187-1196.

      [2] Choi, K., Fazekas, G., Cho, K., & Sandler, M. (2018). The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(2), 139-149.

      [3] Zhang, K., Zhang, H., Li, S., Yang, C., & Sun, L. (2018). The PMEmo Dataset for Music Emotion Recognition. In Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, Yokohama, Japan, pp. 135-142.

      [4] Murthy, Y.V. & Koolagudi, S.G. (2018). Content-Based Music Information Retrieval (CB-MIR) and Its Applications toward the Music Industry: A Review. ACM Computing Surveys, 51(3), Article No. 45.

      [5] Nanni, L., Costa, Y., Lumini, A., & Kim, M. Y. (2017). Combining visual and acoustic features for music genre classification, Expert Systems with Applications, 99(1), 987-996.

      [6] Lee, J. & Kim, D.-W. (2018). Scalable Multilabel Learning Based on Feature and Label Dimensionality Reduction, Complexity 2018(1), 1-15.

      [7] Liu, J., Lin, Y., Li, Y., Weng, W., & Wu, S. (2018). Online multi-label streaming feature selection based on neighborhood rough set. Pattern Recognition, 84, 273-287.

      [8] Lee J., Seo. W., Han. H & Kim, D.-W. (2018). Evolutionary Multilabel Feature Selection Using Promising Feature Subset Generation. Journal of Sensors, 2018(1), 1-12.

      [9] Lee J. & Kim, D.-W. (2017). SCLS: Multi-label feature selection based on scalable criterion for large label set. Pattern Recognition, 66(1), 342-352.

      [10] Panda, R., Malheiro, R.M., & Paiva, R.P. (2018). Novel audio features for music emotion recognition. IEEE Transactions on Affective Computing, doi:10.1109/ TAFFC.2018.2820691.

      [11] Lee J., Seo. W., & Kim, D.-W. (2018). Effective Evolutionary Multilabel Feature Selection under a Budget Constraint. Complexity, 2018(1), 1-14.

      [12] Zhai, E., Li, Z. Li, Z. & Chen, G. (2016). Resisting tag spam by leveraging implicit user behaviors, Proceedings of the VLDB Endowment, 10(3), 241-252.

      [13] Arnaiz-Gonzalez, A., Diez-Pastor, J.-F., Rodriguez, J.J., & Garcia-Osorio, C. (2018). Local sets for multi-label instance selection, Applied Soft Computing, 68(1), 651-666.

      [14] Huang, S., Zhou, L., Liu, Z., Ni, S., & He, J. (2018). Empirical Research on a Fuzzy Model of Music Emotion Classification Based on Pleasure-Arousal Model, In Proceedings of 2018 37th Chinese Control Conference, Wuhan, China, pp. 3239-3244.

      [15] Shao, X., Cheng, Z., & Kankanhalli, M.S. (2018). Music auto-tagging based on the unified latent semantic modeling. Multimedia Tools and Applications, doi:10. 1007/s11042-018-5632-2.

      [16] Lee, J., Jo, J.-H., Lim, H., Chae, J.-H., Lee, S.-U., & Kim, D.-W. (2015). Investigating relation of music data: Emotion and audio signals. Lecture Notes in Electrical Engineering, 330(1), 251-256.

      [17] Pereira, R.B., Plastino, A., Zadrozny, B., & Merschmann L.H. (2018). Categorizing feature selection methods for multi-label classification. Artificial Intelligence Review, 49(1), 57-78.

      [18] Lee, J. & Kim, D.-W. (2013). Feature Selection for Multi-label Classification using Multivariate Mutual Information. Pattern Recognition Letters, 34(3), 349-357.

      [19] Lange, E.B. & Frieler, K. (2018). T6G: Short Talks 6-Emotion Computing. In proceedings of the 15th International Conference on Music Perception and Cognition / 10th Triennial Conference of the European Society for the Cognitive Sciences of Music, Sydney, Australia, p. 35.

  • Downloads

  • How to Cite

    Seo, W., Seo, S., & Lee, J. (2018). Toward Accurate Music Classification Using Local Set-based Multi-label Prototype Selection. International Journal of Engineering & Technology, 7(4.39), 52-55. https://doi.org/10.14419/ijet.v7i4.39.23697