Songs Recognition Using Audio Information Fusion

Authors

  • Paweł Biernacki University of Technology Wroclaw

Abstract

In the article an information fusion approach for song classification using acoustic signal was presented. Many acoustic features can contribute to a right diagnosis of the music. Consisting only one set of features can omit the relevant information. It is possible to improve the accuracy of classification thanks to the technique of information fusion, where various aspects of acoustic ’fingerprint’ are being taken into consideration. Two sets of features of the signal were distinguished: based on frequency analysis (harmonic elements) and based on multidimensional correlation relations. Using SVM and k-NN classifiers identification of the commercial is being made. The music audio signal database was used for the assessment of effectiveness of the proposed solution. Results are showing the improvement the effectiveness of recognizing towards applying only of one features set of the song. words.

References

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

B. Guo, M. Nixon, ”Gait feature subset selection by mutual information”, IEEE Trans Syst Man Cybern Part A 39(1):3646, 2009

M. Munich, ”Bayesian subspace methods for acoustic signature recognition”, Proceedings of the 12th European signal processing conference, pp 14, 2004

G.D. Whitaker,”An Overview of Information Fusion”, DERA, British Crown Copyright 2000

S. Schetzen, ”The Voltera and Wiener Theories of nonlinear systems”, John Wiley & Sons, New York, 1980

P. Biernacki,”Orthogonal Schur-type solution of the nonlinear echocancelling problem”, IEEE ICECS 2007, Piscataway, NJ, 2007

P. Biernacki, J. Zarzycki, ”Multidimensional Nonlinear NoiseCancelling 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

P. Biernacki, ”Strategies for adaptive nonlinear noise reduction VolterraWiener filter structure selection”, Proc. ICECS 2006, Nice, France, December 10-13 2006, cd-rom

S. Haykin, ”Adaptive filter theory”, Upper Saddle River, Prentice Hall 1996

D.T.L. Lee, M. Morf, B. Friedlander, ”Recursive Least-Squares Ladder Estimation Algorithms”, IEEE Trans. on CAS, Vol. 28, pp. 467-481, 1981

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.

Downloads

Published

2015-03-16

Issue

Section

Image Processing