Author: Oliver Kirsebom – Lead Acoustic Data Analyst

On 21-22 November 2019, thirty researchers gathered in Victoria, BC for a workshop on Detection and Classification in Marine Bioacoustics with Deep Learning that has been organized by MERIDIAN and hosted by Ocean Networks Canada. The workshop was attended by about 30 marine biologists, data scientists, and computer scientists, coming from both Canadian coasts and the US. The participants represented a wide spectrum of research organizations including universities, government (Fisheries and Oceans Canada, National Oceanic and Atmospheric Administration), industry (JASCO Applied Sciences, Google, Axiom Data Science), and non-for-profits (Orcasound, OrcaLab). Consisting of a mix of oral presentations, open discussion sessions, and hands-on tutorials, the workshop agenda offered a unique opportunity for the participants from distinctly different domains to engage in conversation about Deep Learning and its promising potential for the detection and classification of underwater sounds. Participants could also explore the functionality and application of the Ketos software package during a 90-min hands-on tutorial. Ketos is an open-source Python package developed by MERIDIAN with the purpose of empowering marine biologists to train their own Deep Learning acoustic models. Presentations given at the workshop can be found under the Presentation Archive on this website.

Categories: News