FN Archimer Export Format
PT J
TI Detecting, classifying, and counting blue whale calls with Siamese neural networks
BT 
AF Zhong, Ming
   Torterotot, Maelle
   Branch, Trevor A.
   Stafford, Kathleen M.
   Royer, Jean-Yves
   Dodhia, Rahul
   Lavista Ferres, Juan
AS 1:1;2:2;3:3;4:4;5:2;6:1;7:1;
FF 1:;2:;3:;4:;5:;6:;7:;
C1 AI for Good Research Lab, Microsoft, Redmond, Washington 98052, USA
   Laboratory Geosciences Ocean, University of Brest and CNRS, Brest, France
   School of Aquatic and Fishery Sciences, University of Washington, Seattle, Washington 98105, USA
   Applied Physics Laboratory, University of Washington, Seattle, Washington 98105, USA
C2 MICROSOFT RES, USA
   UBO, FRANCE
   UNIV WASHINGTON, USA
   UNIV WASHINGTON, USA
UM LGO
IF 2.482
TC 12
UR https://archimer.ifremer.fr/doc/00693/80505/83708.pdf
LA English
DT Article
AB 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. 
PY 2021
PD MAY
SO Journal Of The Acoustical Society Of America
SN 0001-4966
PU Acoustical Society of America (ASA)
VL 149
IS 5
UT 000649114700002
BP 3086
EP 3094
DI 10.1121/10.0004828
ID 80505
ER

EF