Advertisement

Relating Perceptual Feature Space and Context Drift Information in Query by Humming System

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 309)

Abstract

The advancement in the field of music signal processing insists on effective music information retrieval (MIR) techniques. Query by humming (QBH) system is one of the active research areas under MIR. In this paper, we propose a QBH system for automatically retrieving the desired song based on humming query and human perceptual features. In the proposed system, five perceptual features corresponding to four perceptual properties are extracted. Further, the temporal relationship of these features is estimated through the transfer entropy (TE). The trajectory of TE of the target music database is analyzed to find the match for humming query. Series of experiments are conducted to evaluate the effectiveness of the system with 1,200 songs target database and 200 humming queries. The results show that the proposed method is robust in finding desired song automatically with hummed query as input.

Keywords

Context drift Music information retrieval (MIR) Perceptual features Query by humming (QBH) Transfer entropy (TE) 

References

  1. 1.
    Cao, L., Hao, P., Zhou, C.: Music radar: a web-based QBH system. Technical ArticleGoogle Scholar
  2. 2.
    Jian, M.H., Lin, C.H., Chen, A.L.P.: Perceptual analysis for music segmentation. In: Proceedings of the SPIE, Storage and Ret. Methods and Application for Multimedia, vol. 5307, pp. 223–234 (2004)Google Scholar
  3. 3.
    Pohle, T., Pampalk, E., Widmer, G.: Evaluation of frequently used audio features for classification of music into perception categories. In: Proceedings of the 4th International WS on CBMI (2005)Google Scholar
  4. 4.
    Nandedkar, V.: Audio retrieval using multiple feature Vec. In: IJEEE, vol. 1(1) (2011)Google Scholar
  5. 5.
    Zhang, X., Ras, Z.W.: Analysis of sound features for music timbre recognition. In: Proceedings of the IEEE CS International Conference on MUE, Seoul, Korea, pp. 3–8, (2007)Google Scholar
  6. 6.
    Mitrovic, D., Zeppelzauer, M., Breiteneder, C.: Features for content based audio retrieval. Thesis appeared in advances in computers, vol. 78, pp. 71–150 (2010)Google Scholar
  7. 7.
    Sezgin, C., Gunsel, B., Kurt, G.: A New Perceptual Feature Set for Audio Emotion Recognition. Technical Report, Department of Electronic and Communication Engineering, Istanbul Technical University, Turkey (2010)Google Scholar
  8. 8.
    Vorburger, P., Bernstein, A.: Entropy-based concept shift detection. In: Proceedings of the ICDM, IEEE Computer Society, pp. 1113–1118 (2006)Google Scholar
  9. 9.
    Trisiladevi, C.N., Nagappa, U.B.: Perceptive analysis of QBS system through query excerption. In Proceedings of the 2nd International Conference on CCSEIT, ACM, India, pp. 580–586 (2012)Google Scholar
  10. 10.
    Guo, Z., Wang, Q., Liu, G., Guo, J.: A QBH system based on locality sensitive hashing indexes. Elsevier J. Sig. Process. 93(8), 2229–2243 (2013)CrossRefGoogle Scholar
  11. 11.
    Trisiladevi, C.N., Nagappa, U.B.: Progressive filtering using multiresolution histograms for QBH system. In: Proceedings of the 1st ICMCCA, Springer LNEE, India, vol. 213, pp. 253–265 (2013)Google Scholar
  12. 12.
    Jang, J.S.R., Lee, H.R.: A general framework of progressive filtering and its application to QBSH. IEEE Trans. Audio Speech Lang Process 16(2), 350–358 (2008)CrossRefGoogle Scholar
  13. 13.
    Qin, J., Lin, H., Liu, X.: Query by humming systems using melody matching model based on the Genetic Algorithm. J. S/W 6(12), 2416–2420 (2011)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringS.J. College of EngineeringMysoreIndia
  2. 2.Department of Computer Science and EngineeringGovernment Engineering CollegeChamarajanagarIndia

Personalised recommendations