MidiFind: Similarity Search and Popularity Mining in Large MIDI Databases

  • Guangyu XiaEmail author
  • Tongbo Huang
  • Yifei Ma
  • Roger Dannenberg
  • Christos Faloutsos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8905)


While there are perhaps millions of MIDI files available over the Internet, it is difficult to find performances of a particular piece because well labeled metadata and indexes are unavailable. We address the particular problem of finding performances of compositions for piano, which is different from often-studied problems of Query-by-Humming and Music Fingerprinting. Our MidiFind system is designed to search a million MIDI files with high precision and recall. By using a hybrid search strategy, it runs more than 1000 times faster than naive competitors, and by using a combination of bag-of-words and enhanced Levenshtein distance methods for similarity, our system achieves a precision of 99.5 % and recall of 89.8 %.


Music search Similarity search Large scale string matching Data mining Popularity mining MIDI 


  1. 1.
  2. 2.
  3. 3.
    Bastian, M., Heymann, S., Jacomy, M.: Gephi: an open source software for exploring and manipulating networks. In: International AAAI Conference on Weblogs and Social Media (2009)Google Scholar
  4. 4.
    Ciaccia, P., Patella, M., Zezula, P.: M-tree: an effcient access method for similarity search in metric spaces. In: Proceedings of the 23rd Athens International Conference on VLDB, pp. 426–425 (1997)Google Scholar
  5. 5.
    Dannenberg, R.B., Birmingham, W.P., Pardo, B., Hu, N., Meek, C., Tzanetakis, G.: A comparative evaluation of search techniques for query-by-humming using the musart testbed. J. Am. Soc. Inf. Sci. Technol. 58(5), 687–701 (2007)CrossRefGoogle Scholar
  6. 6.
    Ding, H., Trajcevski, G., Scheuermann, P., Wang, X., Keogh, E.: Querying and mining of time series data: experimental comparison of representations and distance measures. Proc. VLDB Endow. 1(2), 1542–1552 (2008)CrossRefGoogle Scholar
  7. 7.
    Ellis, D., Whitman, B., Jehan, T., Lamere, P.: The echo nest musical fingerprint (ENMFP). In: International Symposium on Music Information Retrieval (2010)Google Scholar
  8. 8.
    Ghias, A., Logan, J., Chamberlin, D., Smith, B.C.: Query by humming: musical information retrieval in an audio database. In: ACM Multimedia, pp. 231–236 (1995)Google Scholar
  9. 9.
    Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: Proceedings of the 25th International Conference on Very Large Data Bases, VLDB ’99, pp. 518–529. Morgan Kaufmann Publishers Inc., San Francisco (1999)Google Scholar
  10. 10.
    Haitsma, J., Kalker, T.: A highly robust audio fingerprinting system. In: International Symposium on Music Information Retrieval (2002)Google Scholar
  11. 11.
    Jang, R., Lee, H.: Hierarchical filtering method for content-based music retrieval via acoustic input. In: Proceedings of the ACM Multimedia, pp. 401–410. ACM Press (2001)Google Scholar
  12. 12.
    Krumhansl, C.L.: Cognitive Foundations of Musical Pitch. Oxford University Press, New York (2001)CrossRefGoogle Scholar
  13. 13.
    Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text classification using string kernels. J. Mach. Learn. Res. 2, 419–444 (2002)zbMATHGoogle Scholar
  14. 14.
    Martin, S., Brown, W.M., Klavans, R., Boyack, K.W.: Openord: an open-source toolbox for large graph layout. In: IS&T/SPIE Electronic Imaging, pp. 786806–786806. International Society for Optics and Photonics (2011)Google Scholar
  15. 15.
    Mazzoni, D., Dannenberg, R.B.: Melody matching directly from audio. In: International Symposium on Music Information Retrieval, pp. 17–18 (2001)Google Scholar
  16. 16.
    Mcnab, R.J., Smith, L.A., Bainbridge, D., Witten, I.H.: The new zealand digital library MELody inDEX. D-Lib Mag. 3(5), 4–15 (1997)Google Scholar
  17. 17.
    Paass, G., Leopold, E., Larson, M., Kindermann, J., Eickeler, S.: SVM classification using sequences of phonemes and syllables. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) PKDD 2002. LNCS (LNAI), vol. 2431, p. 373. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  18. 18.
    Papapetrou, P., Athitsos, V., Potamias, M., Kollios, G., Gunopulos, D.: Embedding-based subsequence matching in time-series databases. ACM Trans. Database Syst. (TODS) 36(3), 17 (2011)CrossRefGoogle Scholar
  19. 19.
    Scholkopf, B., Smola, A., Müller, K.R.: Kernel principal component analysis. In: Schölkopf, B., Burges, C.J.C., Smola, A.J. (eds.) Advances in Kernel Methods - Support Vector Learning, pp. 327–352. MIT Press, Cambridge (1999)Google Scholar
  20. 20.
    Shlens, J.: A tutorial on principal component analysis. In: Systems Neurobiology Laboratory, Salk Institute for Biological Studies (2005)Google Scholar
  21. 21.
    Uitdenbogerd, A., Zobel, J.: Manipulation of music for melody matching. In: ACM Multimedia, pp. 235–240 (1998)Google Scholar
  22. 22.
    Uitdenbogerd, A., Zobel, J.: Melodic matching techniques for large music databases. In: Proceedings of the Seventh ACM International Conference on Multimedia (Part 1), Multimedia ’99, pp. 57–66. ACM, New York (1999)Google Scholar
  23. 23.
    Widmer, G., Flossmann, S., Grachten, M.: YQX plays Chopin. AI Mag. 30(3), 35–48 (2009)Google Scholar
  24. 24.
    Widmer, G., Tobudic, A.: Playing Mozart by analogy: learning multi-level timing and dynamics strategies. J. New Music Res. 32(3), 259–268 (2003)CrossRefGoogle Scholar
  25. 25.
    Zhu, Y., Shasha, D.: Warping indexes with envelope transforms for query by humming. In: Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data, SIGMOD ’03, pp. 181–192. ACM, New York (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Guangyu Xia
    • 1
    Email author
  • Tongbo Huang
    • 1
  • Yifei Ma
    • 1
  • Roger Dannenberg
    • 1
  • Christos Faloutsos
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations