EAR-TUKE: The Acoustic Event Detection System

  • Martin Lojka
  • Matúš Pleva
  • Eva Kiktová
  • Jozef Juhár
  • Anton Čižmár
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 429)

Abstract

This paper introduces acoustic events detection system capable of processing continuous input audio stream in order to detect potentially dangerous acoustic events. The system is representing a light, easy extendable, log-term running and complete solution to acoustic event detection. The system is based on its own approach to detection and classification of acoustic events using modified Viterbi decoding process using in combination with Weighted Finite-State Transducers (WFSTs) to support extensibility and acoustic modeling based on Hidden Markov Models (HMMs). Thesystem is completely programmed in C++ language and was designed to be self sufficient and to not require any additional dependencies. Additionally also a signal preprocessing part for feature extraction of Mel-Frequency Cepstral Coefficient(MFCC), Frequency Bank Coefficient (FBANK) and Mel-Spectral Coefficient (MELSPEC) is included. For robustness increase the system contains Cepstral Mean Normalization (CMN) and our proposed removal of basic coefficients from feature vector.

Keywords

Acoustic Event Detection Weighted Finite-State Transducers Continuous Monitoring of Large Urban Areas 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lopatka, K., Kotus, J., Czyzewski, A.: Application of vector sensors to acoustic surveillance of a public interior space. Archives of Acoustics 36, 851–860 (2011)CrossRefGoogle Scholar
  2. 2.
    Lopatka, K., Czyzewski, A.: Acceleration of decision making in sound event recognition employing supercomputing cluster. Information Sciences (2013) (article in press)Google Scholar
  3. 3.
    Lojka, M., Juhár, J.: Fast construction of speech recognition network for Slovak language. Journal of Electrical and Electronics Engineering 3(1), 111–114 (2010)Google Scholar
  4. 4.
    Lee, A., Kawahara, T.: Recent Development of Open-Source Speech Recognition Engine Julius. In: Proc. of the Asia-Pacific Signal and Information Processing Association, Annual Summit and Conference, APSIPA ASC 2009, Sapporo, Japan, pp. 131–137 (2009)Google Scholar
  5. 5.
    Lamere, P., Kwok, P., Gouvea, E., Raj, B., Singh, R., Walker, W., Warmuth, M., Wolf, P.: The CMU SPHINX-4 speech recognition system. In: IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003), Hong Kong, pp. 2–5 (2003)Google Scholar
  6. 6.
    Schliep, A., Georgi, B., Rungsarityotin, W., Costa, I., Schonhuth, A.: The general Hidden Markov Model library: Analyzing systems with unobservable states. In: Proceedings of the Heinz-Billing-Price, pp. 121–135 (2004)Google Scholar
  7. 7.
    Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent Developments in openSMILE, the Munich Open-Source Multimedia Feature Extractor. In: Proc. ACM Multimedia (MM), Barcelona, Spain, pp. 835–838. ACM (2013)Google Scholar
  8. 8.
    Pleva, M., Lojka, M., Juhar, J.: Modified Viterbi decoder for long-term audio events monitoring. Journal of Electrical and Electronics Engineering 5(1), 195–198 (2012)Google Scholar
  9. 9.
    Pleva, M., Lojka, M., Juhar, J., Vozarikova, E.: Evaluating the modified Viterbi decoder for long-term audio events monitoring task. In: Proceedings Elmar - International Symposium Electronics in Marine, pp. 179–182 (2012)Google Scholar
  10. 10.
    Lojka, M., Pleva, M., Juhar, J., Kiktova, E.: Modification of widely used feature vectors for real-time acoustic events detection. In: Proceedings Elmar - International Symposium Electronics in Marine, pp. 199–202 (2013)Google Scholar
  11. 11.
    Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P., The HTK Book Version 3.4. Cambridge University Press (2006)Google Scholar
  12. 12.
    Alam, M.J., Ouellet, P., Kenny, P., O’Shaughnessy, D.: Comparative evaluation of feature normalization techniques for speaker verification. In: Travieso-González, C.M., Alonso-Hernández, J.B. (eds.) NOLISP 2011. LNCS, vol. 7015, pp. 246–253. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Vozáriková, E., Juhár, J., Čižmár, A.: Acoustic events detection using MFCC and MPEG-7 descriptors. In: Dziech, A., Czyżewski, A. (eds.) MCSS 2011. CCIS, vol. 149, pp. 191–197. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  14. 14.
    Mohri, M., Pereira, F.C.N., Riley, M.: Speech recognition with weighted finite-state transducers. In: Springer Handbook of Speech Processing, pp. 1–31 (2008)Google Scholar
  15. 15.
    Rabiner, L.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 257–286 (1989)Google Scholar
  16. 16.
    Dixon, P.R., Hori, C., Kashioka, H.: A comparison of dynamic WFST decoding approaches. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4209–4212 (2012)Google Scholar
  17. 17.
    Pleva, M., Vozarikova, E., Dobos, L., Cizmar, A.: The joint database of audio events and backgrounds for monitoring of urban areas. Journal of Electrical and Electronics Engineering 4(1), 185–188 (2011)Google Scholar
  18. 18.
    Kiktova, E., Lojka, M., Pleva, M., Juhar, J., Cizmar, A.: Comparison of different feature types for acoustic event detection system. In: Dziech, A., Czyżewski, A. (eds.) MCSS 2013. CCIS, vol. 368, pp. 288–297. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  19. 19.
    Sattar, F., Driessen, P.F., Page, W.H.: Automatic event detection for noisy hydrophone data using relevance features. In: Proceedings of the IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing, pp. 383–388 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Martin Lojka
    • 1
  • Matúš Pleva
    • 1
  • Eva Kiktová
    • 1
  • Jozef Juhár
    • 1
  • Anton Čižmár
    • 1
  1. 1.Dept. of Electronics and Multimedia Communications, FEI TU KošiceTechnical University of KošiceKošiceSlovak Republic

Personalised recommendations