期刊
SCIENTIFIC REPORTS
卷 9, 期 -, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41598-019-48909-4
关键词
-
资金
- FNU large frame grant
- Villum Foundation
- Radcliffe Institute Research Partnership Program
- Paul M. Angell Foundation [Con-F18-14]
- Royal Society Wolfson Research Merit Award
- ERC Consolidator Grant [724228]
- FNU
- Carlsberg Foundation expedition grant
- Focused on Nature
- CRE Grant from the National Geographic Society
- Arizona Center for Nature Conservation
- Quarters For Conservation
- Dansk Akustisks Selskab
- Oticon Foundation
- Dansk Tennis Fond
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据