Intelligent System for Commercial Block Recognition Using Audio Signal Only

  • Pawel Biernacki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6276)


In this article the effective method of a single commercial extracting from a advertising block and its recognition using only the audio signal is presented. Proposed algorithm uses a multidimensional orthogonal audio signal representation for a track parametrization. Simulation results for poor commercial audio signal recording conditions and comparison with the known methods are presented. The proposed solution gives a recognition at the level of 98%. This is the result better than the popular methods based on spectral analysis.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kay, S.M.: Modern Spectral Estimation. Prentice Hall, Englewood Cliffs (1988)MATHGoogle Scholar
  2. 2.
    Rabiner, L.: Fundamentals of Speech Recognition. Prentice Hall PTR, Englewood Cliffs (1993)Google Scholar
  3. 3.
    Lienhart, R., Kuhmunch, C., Euelsberg, W.: On the detection and recognition of television commercials. In: Proc. IEEE Conf. on Multimedia Computing and Systems, Ottawa, Canada, pp. 509–516 (June 1997)Google Scholar
  4. 4.
    Zabih, R., Miller, J., Mai, K.: A feature-based algorithm for detecting and classifying scene breaks. In: ACM Conference on Multimedia, San Francisco, California (November 1995)Google Scholar
  5. 5.
    Biernacki, P., Zarzycki, J.: Multidimensional Nonlinear Noise-Cancelling Filters of the Volterra-Wiener Class. In: Proc. 2-Nd Int. Workshop on Multidimensional (nD) Systems (NDS-2000), pp. 255–261. Inst. of Control and Comp. Eng. TU of Zielona Gora Press, Czocha Castle (2000)Google Scholar
  6. 6.
    Biernacki, P., Zarzycki, J.: Orthogonal Schur-Type Solution of the Nonlinear Noise-Cancelling Problem. In: Proc. Int. Conf. On Signals and Electronic Systems (ICSES 2000), Ustron, pp. 337–342 (2000)Google Scholar
  7. 7.
    Lee, D.T.L., Morf, M., Friedlander, B.: Recursive Least-Squares Ladder Estimation Algorithms. IEEE Trans. on CAS 28, 467–481 (1981)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Schetzen, S.: The Voltera & Wiener Theories of nonlinear systems. John Wiley & Sons, New York (1980)Google Scholar
  9. 9.
    Haitsma, J., Kalker, T., Oostveen, J.: Robust audio hashing for content identification. In: Proc. of the Content-Based Multimedia Indexing, Firenze, Italy (September 2001)Google Scholar
  10. 10.
    Morgan, N., Bourlard, H., Hermansky, H.: Automatic Speech Recognition: An Auditory Perspective. In: Greenberg, S., Ainsworth, W.A. (eds.) Speech Processing in the Auditory System, p. 315. Springer, Heidelberg (2004) ISBN 9780387005904Google Scholar
  11. 11.
    Paliwal, K.K.: Spectral subband centroid features for speech recognition. In: Proc. IEEE ICASSP, pp. 617–620 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pawel Biernacki
    • 1
  1. 1.Telecom, Acoustic and Computer Science InstituteWroclaw University of TechnologyWroclawPoland

Personalised recommendations