Advertisement

Using Three Reassigned Spectrogram Patches and Log-Gabor Filter for Audio Surveillance Application

  • Sameh Souli
  • Zied Lachiri
  • Alexander Kuznietsov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)

Abstract

In this paper, we propose a robust environmental sound spectrogram classification approach; its purpose is surveillance and security applications based on the reassignment method and log-Gabor filters. Besides, the reassignment method is applied to the spectrogram to improve the readability of the time-frequency representation, and to assure a better localization of the signal components. In this approach the reassigned spectrogram is passed through a bank of 12 log-Gabor filter concatenation applied to three spectrogram patches, and the outputs are averaged and underwent an optimal feature selection procedure based on a mutual information criterion. The proposed method is tested on a large database consists of 1000 environmental sounds belonging to ten classes. The averaged recognition accuracy is of order 90.87% which obtained using the multiclass support vector machines (SVM’s).

Keywords

Environmental sounds Log-Gabor-Filter Mutual Information Reassignment Method SVM Multiclass 

References

  1. 1.
    Chu, S., Narayanan, S., Kuo, C.C.J.: Environmental Sound Recognition with Time-Frequency Audio Features. IEEE Trans. on Speech, Audio, and Language Processing 17(6), 1142–1158 (2009)CrossRefGoogle Scholar
  2. 2.
    Rabaoui, A., Davy, M., Rossignol, S., Ellouze, N.: Using One-Class SVMs and Wavelets for Audio Surveillance. IEEE Transactions on Information Forensics and Security 3(4), 763–775 (2008)CrossRefGoogle Scholar
  3. 3.
    Yu, G., Slotine, J.J.: Fast Wavelet-based Visual Classification. In: Proc. IEEE International Conference on Pattern Recognition, ICPR, Tampa, pp. 1–5 (2008)Google Scholar
  4. 4.
    Souli, S., Lachiri, Z.: Environmental Sounds Classification Based on Visual Features. In: San Martin, C., Kim, S.-W. (eds.) CIARP 2011. LNCS, vol. 7042, pp. 459–466. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  5. 5.
    Kelly Fitz, R., Sean Fulop, A.: A unified theory of time-frequency reassignment. Computing Research Repository-CORR, abs/0903.3 (2009)Google Scholar
  6. 6.
    Kleinschmidt, M.: Methods for capturing spectro-temporal modulations in automatic speech recognition. Electrical and Electronic Engineering Acoustics, Speech and Signal Processing Papers, Acta Acustica 88, 416–422 (2002)Google Scholar
  7. 7.
    He, L., Lech, M., Maddage, N., Allen, N.: Stress and Emotion Recognition Using Log-Gabor Filter. In: 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII, Amsterdam, pp. 1–6 (2009)Google Scholar
  8. 8.
    Auger, F., Flandrin, P.: Improving the Readability of Time-Frequency and Time-Scale Representations by the Reassignment Method. IEEE Trans. Signal Proc. 40, 1068–1089 (1995)CrossRefGoogle Scholar
  9. 9.
    Chassande-Mottin, E.: Méthodes de réallocation dans le plan temps-fréquence pour l’analyse et le traitement de signaux non stationnaires. PhD thesis, Cergy-Pontoise University (1998)Google Scholar
  10. 10.
    Millioz, F., Martin, N.: Réallocation du spectrogramme pour la détection de frontières de motifs temps-fréquence. In: Colloque GRETSI, pp. 11–14 (2007)Google Scholar
  11. 11.
    Souli, S., Lachiri, Z.: Multiclass Support Vector Machines for Environmental Sounds Classification in visual domain based on Log-Gabor Filters. International Journal of Speech Technology (IJST) 16(2), 203–213 (2013)CrossRefGoogle Scholar
  12. 12.
    Kwak, N., Choi, C.: Input Feature Selection for Classification Problems. IEEE Trans. on Neural Networks 13, 143–159 (2002)CrossRefGoogle Scholar
  13. 13.
    Vladimir, V., Vapnik, N.: An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks 10, 988–999 (1999)CrossRefGoogle Scholar
  14. 14.
    Vapnik, V., Chapelle, O.: Bounds on Error Expectation for Support Vector Machines. Journal Neural Computation 12, 2013–2036 (2000)CrossRefGoogle Scholar
  15. 15.
    Hsu, C.-W., Lin, C.-J.: A comparison of methods for multi-class support vector machines. J. IEEE Transactions on Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  16. 16.
    Hsu, C.-W., Chang, C.-C., Lin, C.-J.: A practical Guide to Support Vector Classification. Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan (2009)Google Scholar
  17. 17.
    The Leonardo Software website, Santa Monica, CA 90401, http://www.leonardosoft.com
  18. 18.
    Fitz, K., Haken, L.: On the Use of Time-Frequency Reassignment in Additive Sound Modeling. J. Audio Eng. Soc. (AES) 50, 879–893 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sameh Souli
    • 1
  • Zied Lachiri
    • 2
  • Alexander Kuznietsov
    • 3
  1. 1.Unité de Recherche Signal, Image et Reconnaissance de FormesÉcole Nationale des Ingénieurs de TunisTunisTunisie
  2. 2.Département Instrumentation et Mesures, INSATInstitut National des Sciences Appliquées et de TechnologieTunisTunisie
  3. 3.University of applied Sciences MittelhessenFriedbergGermany

Personalised recommendations