A total of 147 days spread over 4 years were recorded by a stereophonic sonobuoy set up in the Mediterranean sea, near the coast of Toulon, south of France. These recordings were analyzed in the scope of studying sperm whales (Physeter macrocephalus) and the impact anthropic noises may have on this species. With the use of a novel approach, which combines the use of a stereophonic antenna with a neural network, 226 sperm whales’ passages have been automatically detected in an effective range of 32 km. This dataset was then used to analyze the sperm whales’ abundance, the background noise, the influence of the background noise on the acoustic presence, and the animals’ size. The results show that sperm whales are present all year round in groups of 1–9 individuals, especially during the daytime. The estimated density is 1.69 whales/1000 km$$^2$$
2
. Animals were also less frequent during periods with an increased background noise due to ferries. The animal size distribution revealed the recorded sperm whales were distributed in length from about 7 to 15.5 m, and lonely whales are larger, while groups of two are composed of juvenile and mid-sized animals.
In this paper, we study the difficulties of domain transfer when training deep learning models, on a specific task that is orca vocalization detection. Deep learning appears to be an answer to many sound recognition tasks in human speech analysis as well as in bioacoustics. This method allows to learn from large amounts of data, and find the best scoring way to discriminate between classes (e.g. orca vocalization and other sounds). However, to learn the perfect data representation and discrimination boundaries, all possible data configurations need to be processed. This causes problems when those configurations are ever changing (e.g. in our experiment, a change in the recording system happened to considerably disturb our previously well performing model). We thus explore approaches to compensate on the difficulties faced with domain transfer, with two convolutionnal neural networks (CNN) architectures, one that works in the time-frequency domain, and one that works directly on the time domain.
Classification of transients is a difficult task. In bioacoustics, almost all studies are still done with human labeling. In passive acoustic monitoring (PAM), the data to label are made up from months of continuous recordings with multiple recording stations and the time required to label everything with human labeling is longer than the next recording session will take to produce new data, even with multiple experts. To help lay a foundation for the emergence of automatic labeling of marine mammal transients, we built a dataset using weak labels from a 3TB dataset of marine mammal transients of DCLDE 2018. The DCLDE dataset was made for a click classification challenge. The new dataset has strong labels and opened a new challenge, DOCC10, whose baseline is also described in this paper. The accuracy of 71% of the baseline is already good enough to curate the large dataset, leaving only some regions of interest still to be expertised. But this is far from perfect, and there remains space for future improvement, or challenging alternative techniques. A smaller version of DOCC10 named DOCC7 is also presented.
Passive underwater acoustics allows for the monitoring of the echolocation clicks of cetaceans. Static hydrophone arrays monitor from a fixed location, however, they cannot track animals over long distances. More flexibility can be achieved by mounting hydrophones on a mobile structure. In this paper, we present the design of a small non-uniform array of five hydrophones mounted directly under the Autonomous Surface Vehicle (ASV) Sphyrna (also called an Autonomous Laboratory Vehicle) built by SeaProven in France. This configuration is made challenging by the 40cm aperture of the hydrophone array, extending only two meters below the surface and above the thermocline, thus presenting various artifacts. The array, fixed under the keel of the drone, is numerically stabilized in yaw and roll using the drone's Motion Processing Unit (MPU). To increase the accuracy of the 3D tracking computed from a four hour recording of a Sperm Whale diving several kilometers away, we propose an efficient joint filtering of the clicks in the Time Delay of Arrival (TDoA) space. We show how the DBSCAN algorithm efficiently removes any outlier detection among the thousands of transients, and yields to coherent high definition 3D tracks.
During February and March, 2018, a lone sperm whale known as Yukusam was recorded first by Orcalab in Johnstone Strait and subsequently on multiple hydrophones within the Salish Sea [1]. We learn and denoise these multichannel clicks trains with AutoEncoders Convolutional Neural Net (CNN). Then, we build a map of the echolocations to elucidate variations in the acoustic behavior of this unique animal over time, in different environments and distinct levels of boat noise. If CNN approximates an optimal kernel decomposition, it requires large amounts of data. Via spline functionals we offer analytics kernels with learnable coefficients do reduce it. We [1-3] identify the analytical mother wavelet to represent the input signal to directly learn the wavelet support from scratch by gradient descend on the parameters of cubic splines [2]. Supplemental material http://sabiod.org/yukusam [1] Balestriero, Roger, Glotin, Baraniuk, Semi-Supervised Learning via New Deep Network Inversion, arXiv preprint arXiv:1711.04313, 2017 [2] Balestriero, Cosentino, Glotin, Baraniuk, WaveletNet : Spline Filters for End-to-End Deep Learning, Int. Conf. on MachineLearning, ICML, Stockholm, http://sabiod.org/bib, 2018 [3] Spong P., Symonds H., et al., Joint Observatories Following a Single male Cachalot during 12 weeks—The Yukusam story, ASA 2018.
The bio-sonar of sperm whales presents many specific characteristics, such as its size, its loudness or its vocalization abilities. Furthermore it fulfills several roles in their foraging and social behaviour. However our knowledge about its operation remains limited to the main acoustic path that the emitted pulse may take. We still ignore the precise mechanisms that shape the wave and on which parts the sperm whale is able to act. In this paper, we describe a technique to simulate sperm whale click generation from a physical perspective. Such an approach aims at unveiling the processes involved in their vocal production, as a stepping stone towards a better understanding of their interaction with peers and the environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.