Blind Signal Separation of Similar Pitches and Instruments in a Noisy Polyphonic Domain

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4203)


In our continuing work on ”Blind Signal Separation” this paper focuses on extending our previous work [1] by creating a data set that can successfully perform blind separation of polyphonic signals containing similar instruments playing similar notes in a noisy environment. Upon isolating and subtracting the dominant signal from a base signal containing varying types and amounts of noise, even though we purposefully excluded any identical matches in the dataset, the signal separation system successfully built a resulting foreign set of synthesized sounds that the classifier correctly recognized. Herein, this paper presents a system that classifies and separates two harmonic signals with added noise. This novel methodology incorporates Knowledge Discovery, MPEG7-based segmentation and Inverse Fourier Transforms.


Bayesian Network Independent Component Analysis Independent Component Analysis Musical Instrument Dynamic Bayesian Network 
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.
    Lewis, R., Zhang, X., Ras, Z.: A Knowledge Discovery Model of Identifying Musical Pitches and Instrumentations in Polyphonic Sounds. Special Issue, International Journal of Engineering Applications of Artificial Intelligence (will appear, 2007)Google Scholar
  2. 2.
    Herault, J., Jutten, C.: Space or time adaptive signal processing by neural network models. In: Denker, J.S. (ed.) American Institute of Physics. Neural Networks for Computing, New York, vol. 151, pp. 206–211 (1986)Google Scholar
  3. 3.
    Bingham, E.: Advances In Independent Component Analysis With Applications To Data Mining. Helsinki University of Technology: PhD Dissertation, Helsinki University of Technology, pp. 7–11 (2003)Google Scholar
  4. 4.
    Amari, S., et al.: Multichannel blind deconvolution and equalization using the natural gradient. In: Proc. IEEE Workshop, Signal Processing Advances in Wireless Comm., pp. 101–104 (1997)Google Scholar
  5. 5.
    Smaragdis, P., et al.: Blind separation of convolved mixtures in the frequency domain. In: Proc. IEEE Workshop, IEEE Procedures Neurocomputing, vol. 22, pp. 21–34 (1998)Google Scholar
  6. 6.
    Lambert, R.H., Bell, A.J.: Blind separation of multiple speakers in a multipath environment. In: IEEE Proc. ICASSP, April 1997, pp. 423–426 (1997)Google Scholar
  7. 7.
    Kostek, B., et al.: Estimation of Musical Sound Separation Algorithm Effectiveness Employing Neural Networks. Journal of Intelligent Information Systems 24(2/3), 133–135 (2005)Google Scholar
  8. 8.
    Fujinaga, I., MacMillan, K.: Realtime recognition of orchestral instruments. In: Proceedings of the International Computer Music Conference - Best Presentation Award, pp. 141–143. SpringerHoughton Mifflin Company (2000)Google Scholar
  9. 9.
    Eronen, A., Klapuri, A.: Musical Instrument Recognition Using Cepstral Coefficients and Temporal Features. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 753–756. ICASSP SpringerHoughton Mifflin Company (2000)Google Scholar
  10. 10.
    Zhang, T.: Instrument classification in polyphonic music based on timbre analysis. In: SPIE’s Conference on Internet Multimedia Management Systems, II part of ITCom 2001, Denver, vol. 4519, pp. 136–147 (August 2001)Google Scholar
  11. 11.
    Slezak, D., Synak, P., Wieczorkowska, A., Wroblewski, J.: KDD-based approach to musical instrument sound recognition. In: Hacid, M.-S., Raś, Z.W., Zighed, A.D.A., Kodratoff, Y. (eds.) ISMIS 2002. LNCS (LNAI), vol. 2366, pp. 28–36. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Eronen, A.: Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs. In: Proceedings of Processing and its Applications, ISSPA 2003. Proceedings of the Seventh International Symposium on Signal Processing, Paris, France, July 1-4, pp. 133–136 (2003)Google Scholar
  13. 13.
    Agostini, M., Longar, M., Pollastri, E.: Musical Instrument Timbres Classification with Spectral Features. EURASIP Journal on Applied Signal Processing (1), 5–14 (2003)Google Scholar
  14. 14.
    Kostek, B.: Musical Instrument Classification and Duet Analysis Employing Music Information Retrieval Techniques. Proc. of the IEEE 92(4), 712–729 (2004)CrossRefGoogle Scholar
  15. 15.
    Zweig, O.: Speech Recognition with Dynamic Bayesian Networks, Ph.D. dissertation, Univ. of California, Berkeley, CA (1998)Google Scholar
  16. 16.
    Livescu, K., Glass, J., Bilmes, J.: Hidden Feature Models for Speech Recognition Using Dynamic Bayesian Network. In: Proc. Eurospeech, Geneva, Switzerland, pp. 2529–2532 (September 2003)Google Scholar
  17. 17.
    Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kaufman, San Mateo (1993)Google Scholar
  18. 18.
    Wieczorkowska, A.: Classification of musical instrument sounds using decision trees. In: 8th International Symposium on Sound Engineering and Mastering, ISSEM 1999, pp. 225–230 (1999)Google Scholar
  19. 19.
    le Cessie, S., van Houwelingen, J.: Ridge Estimators in Logistic Regression. Applied Statistics 41(1), 191–201 (1992)zbMATHCrossRefGoogle Scholar
  20. 20.
    Atkeson, C., Moore, A., Schaal, S.: Locally Weighted Learning for Control. Artificial Intelligence Review 11(1-5), 11–73 (1997)CrossRefGoogle Scholar
  21. 21.
    Wieczorkowska, A., et al.: Application of Temporal Descriptors to Musical Instrument Sound. Journal of Intelligent Information Systems, Integrating Artificial Intelligence and Database Technologies 21(1) (July 2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  1. 1.KDD LaboratoryUniversity of North CarolinaCharlotteUSA

Personalised recommendations