Matthias Zeppelzauer
Angela S. Stöger
ABSTRACT
The automated acoustic detection of elephants is an important factor in alleviating the human-elephant conflict in Asia and Africa. In this paper, we present a method for the automated detection of elephant presence and evaluate it on a large dataset of wildlife recordings. We introduce a novel technique for signal enhancement to improve the robustness of the detector in noisy situations. Experiments show that the proposed detector outperforms existing methods and that signal enhancement strongly improves the robustness to noise sources from the environment. The proposed method is a first step towards an automated detection system for elephant presence.
- R. Bardeli. Similarity search in animal sound databases. IEEE Trans. on MM, 11(1):68--76, 2009. Google Scholar
Digital Library
- B. Campana and E. Keogh. A compression-based distance measure for texture. Statistical Analysis and Data Mining, 3(6):381--398, 2010. Google ScholarDigital Library
- P. J. Clemins, M. B. Trawicki, K. Adi, J. Tao, and M. T. Johnson. Generalized perceptual features for vocalization analysis across multiple species. In Proc. of the IEEE Int. Conf. on Acoustics, Speech and Signal Proc., volume 1, pages 253--256, 2006.Google ScholarCross Ref
- C. M. Dissanayake, R. Kotagiri, M. N. Halgamuge, B. Moran, and P. Farrell. Propagation constraints in elephant localization using an acoustic sensor network. In 6th IEEE Int. Conf. on Information and Automation for Sustainability, pages 101--105, 2012.Google ScholarCross Ref
- R. O. Duda, P. E. Hart, and D. G. Stork. Pattern classification. Wiley, 2nd edition, 2001. Google ScholarDigital Library
- D. Greenwood. Critical bandwidth and the frequency coordinates of the basilar membrane. The Journal of the Acoustical Society of America, 33:1344--1356, 1961.Google ScholarCross Ref
- Y. Hao, B. Campana, and E. Keogh. Monitoring and mining animal sounds in visual space. Journal of Insect Behavior, 26(4):466--493, 2012.Google ScholarCross Ref
- C. Harris and M. Stephens. A combined corner and edge detector. In 4th Alvey vision conference, pages 147--151. Manchester, UK, 1988.Google Scholar
- D. K. Mellinger and C. W. Clark. Recognizing transient low-frequency whale sounds by spectrogram correlation. The Journal of the Acoustical Society of America, 107(6):3518--3529, 2000.Google ScholarCross Ref
- C. Santiapillai, S. Wijeyamohan, G. Bandara, R. Athurupana, N. Dissanayake, and B. Read. An assessment of the human-elephant conflict inmboxSrimboxLanka. Ceylon Journal of Science, 39(1):21--33, 2010.Google ScholarCross Ref
- L. Seneviratne, G. Rossel, H. L. Gunasekera, Y. Madanayake, and G. Doluweera. Elephant infrasound calls as a method for electronic elephant detection. In Proc. of the Symp. on Human- Elephant Relationships and Conflicts, pages 1--7, 2004.Google Scholar
- A. Stöger, G. Heilmann, M. Zeppelzauer, A. Ganswindt, S. Hensman, and B. Charlton. Visualizing sound emission of elephant vocalizations: Evidence for two rumble production types. PloS one, 7(11):e48907, 2012.Google ScholarCross Ref
- P. J. Venter and J. J. Hanekom. Automatic detection of african elephant (loxodonta africana) infrasonic vocalisations from recordings. Biosystems engineering, 106(3):286--294, 2010.Google ScholarCross Ref
- J. Wijayakulasooriya. Automatic recognition of elephant infrasound calls using formant analysis and hidden markov model. In 6th IEEE Int. Conf. on Industrial and Information Sys., pages 244--248, 2011.Google ScholarCross Ref
- J. D. Wood, B. McCowan, W. Langbauer, J. Viljoen, and L. Hart. Classification of african elephant loxodonta africana rumbles using acoustic parameters and cluster analysis. Bioacoustics, 15(2):143--161, 2005.Google ScholarCross Ref
Index Terms
- Acoustic detection of elephant presence in noisy environments
Recommendations
Detection, classification and localization of acoustic events in the presence of background noise for acoustic surveillance of hazardous situations
Evaluation of sound event detection, classification and localization of hazardous acoustic events in the presence of background noise of different types and changing intensities is presented. The methods for discerning between the events being in focus ...
A method for enhancing speech and warning signals based on parallel convolutional neural networks in a noisy environment
BACKGROUND:Digital hearing aids are based on technology that amplifies sound and removes noise according to the frequency of hearing loss in hearing loss patients. However, within the noise removed is a warning sound that ...
Joint Dereverberation and Residual Echo Suppression of Speech Signals in Noisy Environments
Hands-free devices are often used in a noisy and reverberant environment. Therefore, the received microphone signal does not only contain the desired near-end speech signal but also interferences such as room reverberation that is caused by the near-end ...
Comments