Songs Recognition Using Audio Information Fusion

• Autorzy: Biernacki P.

Identyfikatory

DOI

10.1515/eletel-2015-0005

• Języki publikacji: EN

Abstrakty

EN

The article presents information fusion approach for song classification with use of acoustic signal. Many acoustic features can contribute to correct identification of a song. Taking into consideration only one set of features may result in omission of relevant information. It is possible to improve the accuracy of identification process by means of the information fusion technique, in which various aspects of acoustic fingerprint are taken into consideration. Two sets of signal features were distinguished: one were based on frequency analysis (harmonic elements) and the other were based on multidimensional correlation ratios. An identification of a commercial was made with use of SVM and k-NN classifiers. The music audio signal database was used for assessing the effectiveness of the proposed solution. Results show an improved effectiveness of identification in relation to applying only one set of song features.

Słowa kluczowe

EN

acoustic identification; signal parametrization; information fusion; Schur coefficients; Bayes' rule

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2015
• Tom: Vol. 61, No. 1
• Strony: 37--41
• Opis fizyczny: Bibliogr. 11 poz., rys., wykr.

Twórcy

autor

Biernacki P.

• University of Technology Wroclaw, Signal Processing Section, 50-350 Wroclaw, Poland

Bibliografia

• [1] T. Damarla, T. Pham, D. Lake , ”An algorithm for classifying multiple targets using acoustic signature”, Proceedings of SPIE signal processing, sensor fusion and target recognition, pp 421427, 2004.
• [2] B. Guo, M. Nixon, ”Gait feature subset selection by mutual information”, IEEE Trans Syst Man Cybern Part A 39(1):3646, 2009.
• [3] M. Munich, ”Bayesian subspace methods for acoustic signature recognition”, Proceedings of the 12th European signal processing conference, pp 14, 2004.
• [4] G.D. Whitaker,”An Overview of Information Fusion”, DERA, British Crown Copyright 2000.
• [5] S. Schetzen, ”The Voltera and Wiener Theories of nonlinear systems”, John Wiley & Sons, New York, 1980.
• [6] P. Biernacki,”Orthogonal Schur-type solution of the nonlinear echo-cancelling problem”, IEEE ICECS 2007, Piscataway, NJ, 2007.
• [7] P. Biernacki, J. Zarzycki, ”Multidimensional Nonlinear Noise-Cancelling Filters of the Volterra-Wiener Class”, Proc. 2-Nd Int. Workshop on Multidimensional (nD) Systems (NDS-2000), ed. Inst. of Control and Comp. Eng. TU of Zielona Gora Press, Czocha Castle, pp. 255-261, 2000.
• [8] P. Biernacki, ”Strategies for adaptive nonlinear noise reduction Volterra-Wiener filter structure selection”, Proc. ICECS 2006, Nice, France, December 10-13 2006, cd-rom.
• [9] S. Haykin, ”Adaptive filter theory”, Upper Saddle River, Prentice Hall 1996.
• [10] D.T.L. Lee, M. Morf, B. Friedlander, ”Recursive Least-Squares Ladder Estimation Algorithms”, IEEE Trans. on CAS, Vol. 28, pp. 467-481, 1981.
• [11] J. Zarzycki, ”Multidimensional Nonlinear Schur Parametrization of NonGaussian Stochastic Signals - Part One: Statement of the Problem”, Multidimensional Systems and Signal Processing (MDSSP) Journ. (Kluwer Academic Publishers), Vol. 15, No. 3, pp. 217-241, 2004.