Using Gaussian mixture models to detect and classify dolphin whistles and pulses

Abstract

In recent years, a number of automatic detection systems for free-ranging cetaceans have been proposed that aim to detect not just surfaced, but also submerged, individuals. These systems are typically based on pattern-recognition techniques applied to underwater acoustic recordings. Using a Gaussian mixture model, a classification system was developed that detects sounds in recordings and classifies them as one of four types: background noise, whistles, pulses, and combined whistles and pulses. The classifier was tested using a database of underwater recordings made off the Spanish coast during 2011. Using cepstral-coefficient-based parameterization, a sound detection rate of 87.5% was achieved for a 23.6% classification error rate. To improve these results, two parameters computed using the multiple signal classification algorithm and an unpredictability measure were included in the classifier. These parameters, which helped to classify the segments containing whistles, increased the detection rate to 90.3% and reduced the classification error rate to 18.1%. Finally, the potential of the multiple signal classification algorithm and unpredictability measure for estimating whistle contours and classifying cetacean species was also explored, with promising results.

Automatic Search and Analysis on Sinusoidal Whistle Signal of Captive Bottlenose Dolphins

“…In the case of marine mammals, a number of research groups are now regularly deploying autonomous recorders which collect data over many months, thereby it is inefficient to observe the biological behavior of bottlenose dolphin full timer artificially. Many methods of automatically detecting and classifying tonal sounds are proposed, including Short Time energy method, Time Frequency(TF) correlation method, Gauss mixture model method and Frequency contour tracing method [8][9][10][11][12] and so on. In this paper, we address Time Frequency correlation method.…”

ShipsEar: An underwater vessel noise database

“…The classifier used for this experiment, which followed this general structure, was derived from a detection and classification system for marine mammals described in detail in [24]. Parametrization was based on cepstral coefficients [25] and statistical classification was based on Gaussian mixture models (GMMs) [26].…”

Automatic classification of whistles from coastal dolphins of the southern African subregion

“…3. (Color online) The success rates from published whistle classification tests run with different numbers of species (red and blue squares show, respectively, the results of this study for the three species-classifier and the four-population classifier; Steiner, 1981;Wang et al, 1995;Matthews et al, 1999;Rendell et al, 1999;Oswald et al, 2003;Oswald et al, 2007;Roch et al, 2007;Gannier et al, 2010;Caillat, 2013;Gillespie et al, 2013;Azzolin et al, 2014;Parada and Cardenal-L opez, 2014;Lin and Chou, 2015).…”