Detecting, classifying, and counting blue whale calls with Siamese neural networks

Type Article
Date 2021-05
Language English
Author(s) Zhong Ming1, Torterotot Maelle2, Branch Trevor A.3, Stafford Kathleen M.4, Royer Jean-Yves2, Dodhia Rahul1, Lavista Ferres Juan1
Affiliation(s) 1 : AI for Good Research Lab, Microsoft, Redmond, Washington 98052, USA
2 : Laboratory Geosciences Ocean, University of Brest and CNRS, Brest, France
3 : School of Aquatic and Fishery Sciences, University of Washington, Seattle, Washington 98105, USA
4 : Applied Physics Laboratory, University of Washington, Seattle, Washington 98105, USA
Source The Journal of the Acoustical Society of America (0001-4966) (Acoustical Society of America (ASA)), 2021-05 , Vol. 149 , N. 5 , P. 3086-3094
DOI 10.1121/10.0004828
Abstract

The goal of this project is to use acoustic signatures to detect, classify, and count the calls of four acoustic populations of blue whales so that, ultimately, the conservation status of each population can be better assessed. We used manual annotations from 350 h of audio recordings from the underwater hydrophones in the Indian Ocean to build a deep learning model to detect, classify, and count the calls from four acoustic song types. The method we used was Siamese neural networks (SNN), a class of neural network architectures that are used to find the similarity of the inputs by comparing their feature vectors, finding that they outperformed the more widely used convolutional neural networks (CNN). Specifically, the SNN outperform a CNN with 2% accuracy improvement in population classification and 1.7%–6.4% accuracy improvement in call count estimation for each blue whale population. In addition, even though we treat the call count estimation problem as a classification task and encode the number of calls in each spectrogram as a categorical variable, SNN surprisingly learned the ordinal relationship among them. SNN are robust and are shown here to be an effective way to automatically mine large acoustic datasets for blue whale calls.

Full Text
File Pages Size Access
Publisher's official version 9 2 MB Open access
Top of the page

How to cite 

Zhong Ming, Torterotot Maelle, Branch Trevor A., Stafford Kathleen M., Royer Jean-Yves, Dodhia Rahul, Lavista Ferres Juan (2021). Detecting, classifying, and counting blue whale calls with Siamese neural networks. The Journal of the Acoustical Society of America, 149(5), 3086-3094. Publisher's official version : https://doi.org/10.1121/10.0004828 , Open Access version : https://archimer.ifremer.fr/doc/00693/80505/