Many marine mammals produce highly nonlinear frequency modulations. Determining the time-frequency support of these sounds offers various applications, which include recognition, localization, and density estimation. This study introduces a low parameterized automated spectrogram segmentation method that is based on a theoretical probabilistic framework. In the first step, the background noise in the spectrogram is fitted with a Chi-squared distribution and thresholded using a Neyman–Pearson approach. In the second step, the number of false detections in time-frequency regions is modeled as a binomial distribution, and then through a Neyman–Pearson strategy, the time-frequency bins are gathered into regions of interest. The proposed method is validated on real data of large sequences of whistles from common dolphins, collected in the Bay of Biscay (France). The proposed method is also compared with two alternative approaches: the first is smoothing and thresholding of the spectrogram; the second is thresholding of the spectrogram followed by the use of morphological operators to gather the time-frequency bins and to remove false positives. This method is shown to increase the probability of detection for the same probability of false alarms.
Skip Nav Destination
Article navigation
September 2013
September 01 2013
Automated segmentation of linear time-frequency representations of marine-mammal sounds
Florian Dadouchi;
Florian Dadouchi
a)
Grenoble Images Parole Signal Automatique Lab, Grenoble Institute of Technology and Centre National de la Recherche Scientifique
, 11 rue des Mathématiques, 38402 Saint-Martin d'Hères, France
Search for other works by this author on:
Cedric Gervaise;
Cedric Gervaise
b)
Chaire Chorus, Foundation of Grenoble Institute of Technology
, 46, Avenue Félix Viallet, 38031 Grenoble Cedex 1, France
Search for other works by this author on:
Cornel Ioana;
Cornel Ioana
Grenoble Images Parole Signal Automatique Lab, Grenoble Institute of Technology and Centre National de la Recherche Scientifique
, 11 rue des Mathématiques, 38402 Saint-Martin d'Hères, France
Search for other works by this author on:
Julien Huillery;
Julien Huillery
Laboratoire Ampère, Ecole Centrale de Lyon
, 36 Avenue Guy de Collongue, 69130 Écully, France
Search for other works by this author on:
Jérôme I. Mars
Jérôme I. Mars
Grenoble Images Parole Signal Automatique Lab, Grenoble Institute of Technology and Centre National de la Recherche Scientifique
, 11 rue des Mathématiques, 38402 Saint-Martin d'Hères, France
Search for other works by this author on:
a)
Author to whom correspondence should be addressed. Electronic mail: florian.dadouchi@gipsa-lab.grenoble-inp.fr
b)
Also at: Grenoble Images Parole Signal Automatique Lab, Grenoble Institute of Technology and Centre National de la Recherche Scientifique, 11 rue des Mathématiques, 38402 Saint-Martin d'Hères, France.
J. Acoust. Soc. Am. 134, 2546–2555 (2013)
Article history
Received:
July 20 2012
Accepted:
May 16 2013
Citation
Florian Dadouchi, Cedric Gervaise, Cornel Ioana, Julien Huillery, Jérôme I. Mars; Automated segmentation of linear time-frequency representations of marine-mammal sounds. J. Acoust. Soc. Am. 1 September 2013; 134 (3): 2546–2555. https://doi.org/10.1121/1.4816579
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Sign in via your Institution
Sign in via your InstitutionPay-Per-View Access
$40.00