Musical Sound Recognition by Active Learning PNN

  • Bülent Bolat
  • Ünal Küçük
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


In this work an active learning PNN was used to recognize instru-mental sounds. LPC and MFCC coefficients with different orders were used as features. The best analysis orders were found by using passive PNNs and these sets were used with active learning PNNs. By realizing some experiments, it was shown that the entire performance was improved by using the active learning algorithm.


Test Accuracy Probabilistic Neural Network Summation Layer Active Learning Process Instrument Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Brown, J.C.: Feature Dependence in the Automatic Identification on Musical Woodwind Instruments. J. Acoust. Soc. Am. 109(3), 1064–1072 (2001)CrossRefGoogle Scholar
  2. 2.
    Eronen, A.: Automatic Musical Instrument Recognition. MsC Thesis at Tampere University of Technology, Dpt. Of Information Technology, Tampere (2001)Google Scholar
  3. 3.
    Eronen, A.: Musical Instrument Recognition Using ICA-Based Transform of Features and Discriminatively Trained HMMs. In: Proc. 7th Int. Symp. Sig. Proc. and Its Applications, pp. 133–136 (2003)Google Scholar
  4. 4.
    Fujinaga, I., MacMillan, K.: Realtime Recognition of Orchestral Instruments. In: Proc. Int. Comp. Mus. Conf., pp. 141–143 (2000)Google Scholar
  5. 5.
    Martin, K.D.: Sound-Source Recognition: A Theory and Computational Model. PhD Thesis at MIT (1999)Google Scholar
  6. 6.
    Bolat, B.: Recognition and Classification of Musical Sounds. PhD Thesis at Yildiz Technical University, Institute of Natural Sciences, Istanbul (2006)Google Scholar
  7. 7.
    Li, D., Sethi, I.K., Dimitrova, N., McGee, T.: Classification of General Audio Data for Content Based Retrieval. Pat. Rec. Lett. 22, 533–544 (2001)MATHCrossRefGoogle Scholar
  8. 8.
    Bolat, B., Yildirim, T.: Active Learning for Probabilistic Neural Networks. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3610, pp. 110–118. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Goh, T.C.: Probabilistic Neural Network For Evaluating Seismic Liquefaction Potential. Canadian Geotechnology Journal 39, 219–232 (2002)CrossRefGoogle Scholar
  10. 10.
    Parzen, E.: On Estimation Of A Probability Density Function And Model. Annals of Mathematical Statistics 36, 1065–1076 (1962)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Hasenjager, M., Ritter, H.: Active Learning In Neural Networks. In: Jain, L. (ed.) New Learning Techniques in Computational Intelligence Paradigms. CRC Press, Florida (2000)Google Scholar
  12. 12.
    RayChaudhuri, T., Hamey, L.G.C.: Minimization Of Data Collection By Active Learning. In: Proc. of the IEEE Int. Conf. Neural Networks (1995) Google Scholar
  13. 13.
    Takizawa, H., Nakajima, T., Kobayashi, H., Nakamura, T.: An Active Learning Algorithm Based On Existing Training Data. IEICE Trans. Inf. & Sys. E83-D (1), 90–99 (2000)Google Scholar
  14. 14.
    Thrun, S.: Exploration In Active Learning. In: Arbib, M. (ed.) Handbook of Brain Science and Neural Networks. MIT Press, Cambridge (1995)Google Scholar
  15. 15.
    Leisch, F., Jain, L.C., Hornik, K.: Cross-Validation With Active Pattern Selection For Neural Network Classifiers. IEEE Trans. Neural Networks 9(1), 35–41 (1998)CrossRefGoogle Scholar
  16. 16.
    Plutowski, M., Halbert, W.: Selecting Exemplars For Training Feedforward Networks From Clean Data. IEEE Trans. on Neural Networks 4(3), 305–318 (1993)CrossRefGoogle Scholar
  17. 17.
    Tong, S., Koller, D.: Active Learning For Parameter Estimation In Bayesian Networks. In: Proc. of Advances in Neural Information Processing Systems, Denver, Colorado, USA (2000)Google Scholar
  18. 18.
    RayChaudhuri, T., Hamey, L.G.C.: Active Learning For Nonlinear System Identification And Control. In: Gertler, J.J., Cruz, J.B., Peshkin, M. (eds.) Proc. IFAC World Congress 1996, San Fransisco, USA, pp. 193–197 (1996)Google Scholar
  19. 19.
    Saar-Tsechansky, M., Provost, F.: Active Learning For Class Probability Estimation And Ranking. In: Proc. of Seventeenth International Joint Conference on Artificial Intelligence (IJCAI 2001), Seattle, WA, USA (2001)Google Scholar
  20. 20.
    Munro, P.W.: Repeat Until Bored: A Pattern Selection Strategy. In: Moody, J., Hanson, S., Lippmann, R. (eds.) Proc. Advances in Neural Information Processing Systems (NIPS 1991), pp. 1001–1008 (1991)Google Scholar
  21. 21.
    Bolat, B., Yildirim, T.: Performance Increasing Methods for Probabilistic Neural Networks. Information Technology Journal 2(3), 250–255 (2003)CrossRefGoogle Scholar
  22. 22.
    Bolat, B., Yildirim, T.: A Data Exchange Method for Probabilistic Neural Networks. Journal of Electrical & Electronics Engineering 4(2), 1137–1140 (2004)Google Scholar
  23. 23.
    Bolat, B., Yildirim, T.: A Dara Selection Method for Probabilistic Neural Networks. In: Proc. International Turkish Symposium On Artificial Intelligence and Neural Networks (TAINN 2003), vol. E-1, pp. 34–35 (2003)Google Scholar
  24. 24.
    Slaney, M.: Auditory Toolbox 2. Tech. Rep. #1998-010 Interval Research Corp. (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bülent Bolat
    • 1
  • Ünal Küçük
    • 1
  1. 1.Electronics and Telecommunications Engineering Dpt.Yildiz Technical UniversityIstanbulTurkey

Personalised recommendations