Imperial College London
Portrait Picture

ProfessorMichaelBronstein

Faculty of Engineering, Department of Computing

Visiting Professor
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Bermant:2019:10.1038/s41598-019-48909-4,
author = {Bermant, PC and Bronstein, MM and Wood, RJ and Gero, S and Gruber, DF},
doi = {10.1038/s41598-019-48909-4},
journal = {Sci Rep},
title = {Deep Machine Learning Techniques for the Detection and Classification of Sperm Whale Bioacoustics.},
url = {http://dx.doi.org/10.1038/s41598-019-48909-4},
volume = {9},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We implemented Machine Learning (ML) techniques to advance the study of sperm whale (Physeter macrocephalus) bioacoustics. This entailed employing Convolutional Neural Networks (CNNs) to construct an echolocation click detector designed to classify spectrograms generated from sperm whale acoustic data according to the presence or absence of a click. The click detector achieved 99.5% accuracy in classifying 650 spectrograms. The successful application of CNNs to clicks reveals the potential of future studies to train CNN-based architectures to extract finer-scale details from cetacean spectrograms. Long short-term memory and gated recurrent unit recurrent neural networks were trained to perform classification tasks, including (1) "coda type classification" where we obtained 97.5% accuracy in categorizing 23 coda types from a Dominica dataset containing 8,719 codas and 93.6% accuracy in categorizing 43 coda types from an Eastern Tropical Pacific (ETP) dataset with 16,995 codas; (2) "vocal clan classification" where we obtained 95.3% accuracy for two clan classes from Dominica and 93.1% for four ETP clan types; and (3) "individual whale identification" where we obtained 99.4% accuracy using two Dominica sperm whales. These results demonstrate the feasibility of applying ML to sperm whale bioacoustics and establish the validity of constructing neural networks to learn meaningful representations of whale vocalizations.
AU  - Bermant,PC
AU  - Bronstein,MM
AU  - Wood,RJ
AU  - Gero,S
AU  - Gruber,DF
DO  - 10.1038/s41598-019-48909-4
PY  - 2019///
TI  - Deep Machine Learning Techniques for the Detection and Classification of Sperm Whale Bioacoustics.
T2  - Sci Rep
UR  - http://dx.doi.org/10.1038/s41598-019-48909-4
UR  - https://www.ncbi.nlm.nih.gov/pubmed/31467331
VL  - 9
ER  -
Download