Acoustic recordings of North Atlantic right whale upcalls in the Gulf of St. Lawrence

Simard, Yvan

https://ror.org/02qa1x782;-;https://ror.org/049jtt335;-

Fisheries and Oceans Canada; Maurice Lamontagne Institute; Université du Québec à Rimouski; Marine Sciences Institute

Kirsebom, Oliver S.

https://ror.org/01e6qks80;-

Dalhousie University; Institute for Big Data Analytics

Frazao, Fabio

https://ror.org/01e6qks80;-

Dalhousie University; Institute for Big Data Analytics

Roy, Nathalie

https://ror.org/02qa1x782;-

Fisheries and Oceans Canada; Maurice Lamontagne Institute

Matwin, Stan

https://ror.org/01e6qks80;-;https://ror.org/01dr6c206;-

Dalhousie University; Institute for Big Data Analytics; Polish Academy of Sciences; Institute of Computer Sciences

Giard, Samuel

https://ror.org/02qa1x782;-

Fisheries and Oceans Canada; Maurice Lamontagne Institute

2020-04-25T00:51:32Z

2020-04-25T00:51:32Z

2020-04-24

https://www.frdr-dfdr.ca/repo/dataset/4a3113e6-1d58-6bb4-aaf2-a9adf75165be

https://doi.org/10.20383/101.0241

The acoustic data were collected between 2015 and 2019 at six stations in the southern Gulf of St. Lawrence using two different deployment configurations. The dataset also includes audio samples from the Gulf of Maine recorded in 2009, which were part of the DCLDE 2013 Challenge dataset (https://soi.st-andrews.ac.uk/static/soi/dclde2013/documents/WorkshopDataset2013.pdf).

The acoustic data are supplemented by expert annotations indicating the presence/absence of North Atlantic right whale upcalls. Spectrogram images are also provided.

These data have been used to train a deep neural network to detect North Atlantic right whale upcalls, as described in the article "Performance of a Deep Neural Network at Detecting North Atlantic Right Whale Upcalls" by Kirsebom, Frazao, Simard, Roy, Matwin, and Giard (doi:10.1121/10.0001132), which also contains a detailed description of the data.

The software developed as part of this work is available on Zenodo (doi:10.5281/zenodo.3736625) under a GPLv3 license. This includes Python scripts for building training and test datasets, computing signal-to-noise ratios, visualizing spectrograms, training the deep neural network, and using the network to analyze continuous audio recordings.

Federated Research Data Repository / dépôt fédéré de données de recherche

Creative Commons Attribution 4.0 International (CC BY 4.0)

https://creativecommons.org/licenses/by/4.0/

North Atlantic right whale

Passive Acoustic Monitoring

Underwater Acoustics

Signal Processing

Deep Neural Networks

Eubalaena glacialis

Acoustic recordings of North Atlantic right whale upcalls in the Gulf of St. Lawrence

f163c1b3-9c88-42f6-a7bb-5839ed6c4063

/1/published/publication_239/

AIP generation and transfer successful

2020-04-25 12:40:35

2020

Dataset

https://doi.org/10.1121/10.0001132

https://doi.org/10.5281/zenodo.3736625

48.0 -63.0

42.5 -69.0

47.0 -65.0 49.0 -60.0

41.0 -71.0 43.0 -67.0

Gulf of St. Lawrence;-;-;-

Gulf of Maine;-;-;-

Natural Sciences and Engineering Research Council of Canada (NSERC)

249977

Discovery Grant

Fisheries and Oceans Canada (DFO)

Ocean and Freshwater Science Contribution Program (OFSCP)

RDF1061001

Biological sciences

Zoology

Animal behaviour

Sciences biologiques

Zoologie

Comportement animal