Content-Based Music Classification by Advanced Features and Progressive Learning

  • Ja-Hwung SuEmail author
  • Chu-Yu Chin
  • Tzung-Pei Hong
  • Jung-Jui Su
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11432)


Recently, content-based music information retrieval has been proposed as a support to facilitate music recommendation, music recognition and music retrieval. For music recognition, although it has been investigated by many studies, it is still a challenging issue for how to effectively learn from music contents. Actually, effective music recognition is achieved by considering two factors, namely feature content and learning strategy. Therefore, in this paper, a content-based music classifier named Progressive-Learning- based Music Classifier (PLMC) is proposed to aim at issues of feature content and learning strategy. In terms of feature content, the audio features are upgraded as the advanced features to enhance quality of features. In terms of learning strategy, a progressive learning strategy is proposed by fusing K-Nearest-Neighbor learning and Support Vector Machine learning. Through the proposed progressive learning, the better classification precision can be reached. The experimental results on real music data show the proposed idea performs better than the state-of-the-arts methods in classifying music.


Music classification Advanced features Progressive learning K-Nearest-Neighbor Support Vector Machine 



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.
    Abe, S.: Fuzzy support vector machines for multilabel classification. Pattern Recogn. 48(6), 2110–2117 (2015)CrossRefGoogle Scholar
  2. 2.
    Ahsan, H., Kumar, V., Jawahar, C.V.: Multi-label annotation of music. In: Proceedings of the Eighth International Conference on Advances in Pattern Recognition (ICAPR) (2015)Google Scholar
  3. 3.
    Bergstra, J., Casagrande, N., Erhan, D., Eck, D., Kégl, B.: Aggregate features and AdaBoost for music classification. Mach. Learn. 65(2–3), 473–484 (2006)CrossRefGoogle Scholar
  4. 4.
    Choi, K., Lee, J.H., Downie, J.S.: What is this song about anyway? Automatic classification of subject using user interpretations and lyrics. In: Proceedings of the 14th ACM/IEEE-CS Joint Conference on Digital Libraries (2014)Google Scholar
  5. 5.
    Chen, Y.A., Yang, Y.H., Wang, J.C., Chen, H.: The AMG1608 dataset for music emotion recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015)Google Scholar
  6. 6.
    Fang, J., Grunberg, D., Litman, D., Wang, Y.: Discourse analysis of lyric and lyric-based classification of music. In: Proceedings of the 18th International Society for Music Information Retrieval Conference (2017)Google Scholar
  7. 7.
    Fu, Z., Lu, G., Ting, K.M., Zhang, D.: A survey of audio-based music classification and annotation. IEEE Trans. Multimedia 13(2), 303–319 (2011)CrossRefGoogle Scholar
  8. 8.
    Goienetxea, I., MartõÂnez-Otzeta, J.M., Sierra, B., Mendialdua, I.: Towards the use of similarity distances to music genre classification: a comparative study. PLoS ONE 13(2), e0191417 (2018)CrossRefGoogle Scholar
  9. 9.
    Huang, Y.F., Lin, S.M., Wu, H.Y., Li, Y.S.: Music genre classification based on local feature selection using a self-adaptive harmony search algorithm. Data Knowl. Eng. 92, 60–76 (2014)CrossRefGoogle Scholar
  10. 10.
    Jao, P.K., Yang, Y.H.: Music annotation and retrieval using unlabeled exemplars: correlation and sparse codes. IEEE Signal Process. Lett. 22(10), 1771–1775 (2015)CrossRefGoogle Scholar
  11. 11.
    Lee, C.H., Lin, H.S., Chen, L.H.: Music classification using the bag of words model of modulation spectral features. In: Proceedings of the 15th International Symposium on Communications and Information Technologies (ISCIT) (2015)Google Scholar
  12. 12.
    Mandel, M.I., Ellis, D.P.W.: Song-level features and support vector machines for music classification. In: Proceedings of the 18th International Society for Music Information Retrieval Conference (2005)Google Scholar
  13. 13.
    Pálmason, H., Jónsson, B.Þ., Amsaleg, L., Schedl, M., Knees, P.: On competitiveness of nearest-neighbor-based music classification: a methodological critique. In: Beecks, C., Borutta, F., Kröger, P., Seidl, T. (eds.) SISAP 2017. LNCS, vol. 10609, pp. 275–283. Springer, Cham (2017). Scholar
  14. 14.
    Reed, J., Lee, C.H.: On the importance of modeling temporal information in music tag annotation. In: Proceedings of International Symposium on Acoustics, Speech and Signal Processing (2009)Google Scholar
  15. 15.
    Santos, A.M., Canuto, A.M.P., Neto, A.F.: A comparative analysis of classification methods to multi-label tasks in different application domains. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. 3, 218–227 (2011)Google Scholar
  16. 16.
    Saari, P., Fazekas, G., Eerola, T., Barthet, M., Lartillot, O., Sandler, M.: Genre-adaptive semantic computing and audio-based modelling for music mood annotation. IEEE Trans. Affect. Comput. 7(2), 122–135 (2016)CrossRefGoogle Scholar
  17. 17.
    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 (2017)Google Scholar
  18. 18.
    Serrà, J., Müller, M., Grosche, P., Arcos, J.L.: Unsupervised music structure annotation by time series structure features and segment similarity. IEEE Trans. Multimedia 16(5), 1229–1240 (2014)CrossRefGoogle Scholar
  19. 19.
    Su, J.H., Tsai, Y.C., Tseng, V.S.: Empirical analysis of multi-labeling algorithms for music emotion annotation. In: Proceedings of ICME 2013 Workshop on Affective Analysis in Multimedia (AAM) (2013)Google Scholar
  20. 20.
    Tian, M., Sandler, M.B.: Towards music structural segmentation across genres: features, structural hypotheses, and annotation principles. ACM Trans. Intell. Syst. Technol. 8(2), 23 (2017)Google Scholar
  21. 21.
    Tsaptsinos, A.: Lyrics-based music genre classification using a hierarchical attention network. In: Proceedings of the 18th International Society for Music Information Retrieval Conference (2017)Google Scholar
  22. 22.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ja-Hwung Su
    • 1
    Email author
  • Chu-Yu Chin
    • 2
  • Tzung-Pei Hong
    • 3
    • 4
  • Jung-Jui Su
    • 5
  1. 1.Department of Information ManagementCheng Shiu UniversityKaohsiungTaiwan
  2. 2.Telecommunication LaboratoriesChunghwa Telecom Company Ltd.TaoyuanTaiwan
  3. 3.Department of Computer Science and Information EngineeringNational University of KaohsiungKaohsiungTaiwan
  4. 4.Department of Computer Science and EngineeringNational Sun Yat-sen UniversityKaohsiungTaiwan
  5. 5.Department of Computer Science and Information EngineeringChinese Culture UniversityTaipeiTaiwan

Personalised recommendations