Music Classification by Automated Relevance Feedbacks

  • Ja-Hwung Su
  • Tzung-Pei HongEmail author
  • Hsuan-Hao Yeh
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1178)


Music recognition systems help users and music platform developers analyze what genre a music piece belongs to. In this paper, we propose an effective automatic music recognition system to help developers effectively tag music with genres. First, we extract Mel-Frequency Cepstral Coefficients (MFCCs) as the basic features. We then transform MFCCs into a set of conceptual features by Support Vector Machine (SVM). By the conceptual features, a automatic relevance feedback method is performed to generate a navigation model, which can be viewed as a recognition model. In the recognition phase, the proposed approach, called music classification by navigation paths (MCNP) uses these conceptual features to recognize the unknown music. The experimental results show that the proposed method is more promising than the state-of-the-arts on music classification.


Music recognition Acoustic features Conceptual features Relevance feedback 



This research was supported by Ministry of Science and Technology, Taiwan, R.O.C. under grant no. MOST 107-2221-E-230-010.


  1. 1.
    Alexandre-Cortizo, E., Rosa-Zurera, M., Lopes-Ferreras, F.: Application of fisher linear discriminant analysis to speech/music classification. In: Proceedings of the International Conference on Computer as a Tool, Serbia (2005)Google Scholar
  2. 2.
    Chen, Y.T.: Music retrieval by learning from automated logs with semantic features. National Sun Yat-sen University (2017)Google Scholar
  3. 3.
    Costa, U.M.G., Oliveira, L.S., Silla Jr., C.N.: An evaluation of convolutional neural networks for music classification using spectrograms. Appl. Soft Comput. 52, 28–38 (2017)CrossRefGoogle Scholar
  4. 4.
    Lidy, T., Rauber, A.: Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. In: Proceedings of the 6th International Conference on Music Information Retrieval (ISMIR), UK, pp. 34–41 (2005)Google Scholar
  5. 5.
    Rocchio, J.J.: Relevance feedback in information retrieval. In: Proceedings of the SMART Retrieval System – Experiment in Automatic Document Processing, pp. 313–323. Prentice-Hall (1971)Google Scholar
  6. 6.
    Su, J.H., Chin, C.Y., Hong, T.P., Su, J.J.: Content-based music classification by advanced features and progressive learning. In: Proceedings of the 11th Asian Conference on Intelligent Information and Database Systems, Yogyakarta, Indonesia, 8–11 April 2019Google Scholar
  7. 7.
    Su, J.H., Huang, W.J., Yu, P.S., Tseng, V.S.: Efficient relevance feedback for content-based image retrieval by mining user navigation patterns. IEEE Trans. Knowl. Data Eng. 23(3), 360–372 (2011)CrossRefGoogle Scholar
  8. 8.
    Su, J.H., Hong, T.P., Chen, Y.T.: Fast music retrieval with advanced acoustic features. In: Proceedings of IEEE International Conference on Consumer Electronics, Taipei, Taiwan (2017)Google Scholar
  9. 9.
    Xu, C., Maddage, N.C., Shao, X., Cao, F., Tian, Q.: Musical genre classification using support vector machines. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Hong Kong (2003)Google Scholar
  10. 10.

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Information ManagementCheng Shiu UniversityKaohsiungTaiwan
  2. 2.Department of Computer Science and Information EngineeringNational University of KaohsiungKaohsiungTaiwan
  3. 3.Department of Computer Science and EngineeringNational Sun Yat-sen UniversityKaohsiungTaiwan

Personalised recommendations