GBED: group based event detection method for audio sensor networks

ABSTRACT

Audio event detection is one of the most important applications in the multimedia sensor networks. In this paper, we present a Group Based Event Detection method, called GBED, to detect the audio events in the audio sensor networks. In the proposed method, we train the basic audio events separately based on statistical learning, and combine them together by some prior knowledge in specific domains. By using GBED we can combine the statistical learning and human knowledge together and reduce the training complexity for complex real-world situations. We deploy this approach on an audio sensor network to evaluate its performance, and the experiment evaluations demonstrate that GBED can achieve satisfied results.

REFERENCES

• 1: C. Clavel, T. Ehrette, G. Richard, "Events detection for an audio-based surveillance system." In Proc. IEEE ICME05, July 2005, Amsterdam, Netherlands, pp.1306--1309.
• 2: S. Moncrieff, S. Venkatesh, G. West, "On-line background determination for complex audio environments." ACM Transaction on Multimedia Computing, Communications, and Applications. Vol.3, Issue 2, May. 2007.
• 3: R Cai, L.Lie, A. Hanjalic, H. J .Zhang and L. H. Cai, "A flexible framework for key audio effects detection and auditory context inference." IEEE Transactions on Audio, Speech, and Language Processing, Vol.14, Issue 3, May 2006, pp.1026--1039.
• 4: A.F. Smeaton, M. McHugh, "Towards event detection in an audio-based sensor network." Multimedia Systems, Vol.12, Issue 3, Dec 2006, pp.179--194.
• 5: Q.Li, H.D. Ma, Q.Huang. "A Hierarchical Framework for Audio Scene Analysis in Sensor Networks". In Proc. IRADSN2009, May 2009, Hangzhou, China, pp.170--177.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.5 Sound and Music Computing

General Terms:
Algorithms, Design, Experimentation

Keywords:
audio event detection, audio sensor networks, audio surveillance systems