Skip to main content
SpringerLink
Log in

A sequential pattern mining approach to design taxonomies for hierarchical music genre recognition

  • Theoretical Advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

In this paper, music genre taxonomies are used to design hierarchical classifiers that perform better than flat classifiers. More precisely, a novel method based on sequential pattern mining techniques is proposed for the extraction of relevant characteristics that enable to propose a vector representation of music genres. From this representation, the agglomerative hierarchical clustering algorithm is used to produce music genre taxonomies. Experiments are realized on the GTZAN dataset for performances evaluation. A second evaluation on GTZAN augmented by Afro genres has been made. The results show that the hierarchical classifiers obtained with the proposed taxonomies reach accuracies of 91.6 % (more than 7 % higher than the performances of the existing hierarchical classifiers).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. http://www.ifs.tuwien.ac.at/mir/audiofeatureextraction.html.

  2. http://marsyas.sness.net/.

  3. http://www.cs.waikato.ac.nz/ml/weka/.

References

  1. Tietche BH, Romain O, Denby B, De Dieuleveult F (2012) FPGA-based simultaneous multichannel fm broadcast receiver for audio indexing applications in consumer electronics scenarios. IEEE Trans Consum Electron 58(4):1153–1161

    Article  Google Scholar 

  2. Brecheisen S, Kriegel H-P, Kunath P, Pryakhin A (2006) Hierarchical genre classification for large music collections. In: Multimedia and expo, 2006 IEEE international conference on, pp 1385–1388

  3. Costa E, Lorena A, Carvalho ACPLF, Freitas A (2007) A review of performance evaluation measures for hierarchical classifiers. In: Evaluation methods for machine learning II: papers from the AAAI-2007 workshop, pp 1–6

  4. Li T, Ogihara M (2005) Music genre classification with taxonomy. In: Acoustics, speech, and signal processing, 2005. In: Proceedings.(ICASSP’05). IEEE international conference on, vol. 5, pp. v-197

  5. Silla Jr CN, Freitas A et al (2009) Novel top-down approaches for hierarchical classification and their application to automatic music genre classification. In: Systems, man and cybernetics, 2009. SMC 2009. IEEE international conference on, pp 3499–3504

  6. Burred JJ, Lerch A (2003) A hierarchical approach to automatic musical genre classification. In: Proceedings of the 6th international conference on digital audio effects, pp 8–11

  7. Ariyaratne HB, Zhang D (2012) A novel automatic hierarchical approach to music genre classification. In: Multimedia and expo workshops (ICMEW), 2012 IEEE international conference on, pp 564–569

  8. Bağcı U, Erzin E (2005) Boosting classifiers for music genre classification. Comput Inf Sci-ISCIS 2005:575–584

    Google Scholar 

  9. Shao X, Xu C, Kankanhalli MS (2004) Unsupervised classification of music genre using hidden markov model. In: Multimedia and expo, 2004. ICME’04. 2004 IEEE international conference on, vol 3, pp 2023–2026

  10. Pachet F, Cazaly D et al (2000) A taxonomy of musical genres. RIAO, pp 1238–1245

  11. http://marsyasweb.appspot.com/download/data_sets/

  12. Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques

  13. Aggarwal CC, Wolf JL, Yu PS, Procopiuc C, Park JS (1999) Fast algorithms for projected clustering. ACM SIGMoD Rec 28(2):61–72

    Article  Google Scholar 

  14. Doraisamy S, Golzari S, Mohd N, Sulaiman MN, Udzir NI (2008) A study on feature selection and classification techniques for automatic genre classification of traditional malay music. In: ISMIR, pp 331–336

  15. Conklin D (2009) Melody classification using patterns. In: Second international workshop on machine learning and music, pp 37-41

  16. Lin C-R, Liu N-H, Wu Y-H, Chen ALP (2004) Music classification using significant repeating patterns. Database systems for advanced applications, pp 506–518

  17. Ren J-M, Chen Z-S, Jang JSR (2010) On the use of sequential patterns mining as temporal features for music genre classification. In: IEEE international conference on acoustics speech and signal processing (ICASSP), pp 2294–2297

  18. Ren J-M, Jang JSR (2011) Time-constrained sequential pattern discovery for music genre classification. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 173–176

  19. Pei J, Han J, Mortazavi-Asl B, Pinto H, Chen Q, Dayal U, Hsu M-C (2001) Prefixspan: mining sequential patterns efficiently by prefix-projected pattern growth. ICCCN, pp 02-15

  20. Agrawal R, Srikant R (1994) Fast algorithms for mining association rules. In: Proceedings of 20th international conference on very large data bases. VLDB 1215:487–499

  21. Srikant R, Agrawal R (1996) Mining quantitative association rules in large relational tables. ACM SIGMOD Rec 25(2):1–12

    Article  Google Scholar 

  22. Zaki MJ (2000) Scalable algorithms for association mining. IEEE Trans Knowl Data Eng 12(3):372–390

    Article  Google Scholar 

  23. Han J, Pei J, Mortazavi-Asl B, Chen Q, Dayal U, Hsu M-C (2000) FreeSpan: frequent pattern-projected sequential pattern mining. In: Proceedings of the sixth ACM SIGKDD international conference on knowledge discovery and data mining, pp 355–359

  24. Rao VCS, Sammulal P (2013) Survey on sequential pattern mining algorithms. Int J Comput Appl 76(12):24–31

    Google Scholar 

  25. George T, Georg E, Perry C (2001) Automatic musical genre classification of audio signals. In: Proceedings of the 2nd international symposium on music information retrieval, Indiana

  26. Mitrović D, Zeppelzauer M, Breiteneder C (2010) Features for content-based audio retrieval. Adv Comput 78:71–150

    Article  Google Scholar 

  27. Lidy T, Rauber A (2005) Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. ISMIR, pp 34-41

  28. www.ifs.tuwien.ac.at/mir/muscle/del/audio_extraction_tools.html

  29. Sudhir R (2011) A survey on image mining techniques: theory and applications. Comput Eng Intell Syst 2(6):44–53

    Google Scholar 

  30. Asghar MN, Hussain F, Manton R (2014) Video indexing: a survey. framework, vol 3(01)

  31. Fernando B, Fromont E, Tuytelaars T (2012) Effective use of frequent itemset mining for image classification. In: European conference on computer vision, pp 214–227

  32. Lesh N, Zaki MJ, Oglhara M (2000) Scalable feature mining for sequential data. Intell Syst Appl 15(2):48–56

    Article  Google Scholar 

  33. Sturm BL (2012) An analysis of the GTZAN music genre dataset. In: Proceedings of the second international ACM workshop on music information retrieval with user-centered and multimodal strategies, pp 7–12

  34. Iloga S, Romain O, Bendaouia L, Tchuente M (2014) Musical genres classification using Markov models. In: Audio, language and image processing (ICALIP), 2014 international conference on, pp 701–705

  35. http://fr.wikipedia.org/wiki/GenreName

  36. http://meka.sourceforge.net/

  37. da Silva V, and Winck AT (2014) Multi-label classification of music into genres

  38. Nicolas Scaringella, Giorgio Zoia, Daniel Mlynek (2006) Automatic genre classification of music content: a survey. Signal Processing Magazine 23(2):133–141

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Higher Teachers’ Training College, Department of Computer Science, University of Maroua, P.O. Box 55, Maroua, Cameroon

    Sylvain Iloga

  2. Laboratoire ETIS, UMR 8051, Université de Cergy-Pontoise, CNRS, ENSEA, av du ponceau, 95000, Cergy-Pontoise, France

    Sylvain Iloga & Olivier Romain

  3. IRD UMI 209 UMMISCO and LIRIMA, University of Yaounde 1, P.O. Box 337, Yaounde, Cameroon

    Sylvain Iloga & Maurice Tchuenté

Authors
  1. Sylvain Iloga
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Olivier Romain
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maurice Tchuenté
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sylvain Iloga.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Iloga, S., Romain, O. & Tchuenté, M. A sequential pattern mining approach to design taxonomies for hierarchical music genre recognition. Pattern Anal Applic 21, 363–380 (2018). https://doi.org/10.1007/s10044-016-0582-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-016-0582-7

Keywords

Search

Navigation