Jiang, J.-J., Bu, L.-R., Duan, F.-J. et al. (4 more authors) (2019) Whistle detection and classification for whales based on convolutional neural networks. Applied Acoustics, 150. pp. 169-178. ISSN 0003-682X
Abstract
Passive acoustic observation of whales is an increasingly important tool for whale research. Accurately detecting whale sounds and correctly classifying them into corresponding whale species are essential tasks, especially in the case when two species of whales vocalize in the same observed area. Whistles are vital vocalizations of toothed whales, such as killer whales and long-finned pilot whales. In this paper, based on deep convolutional neural networks (CNNs), a novel method is proposed to detect and classify whistles of both killer whales and long-finned pilot whales. Compared with traditional methods, the proposed one can automatically learn the sound characteristics from the training data, without specifying the sound features for classification and detection, and thus shows better adaptability to complex sound signals. First, the denoised sound to be analyzed is sent to the trained detection model to estimate the number and positions of the target whistles. The detected whistles are then sent to the trained classification model, which determines the corresponding whale species. A GUI interface is developed to assist with the detection and classification process. Experimental results show that the proposed method can achieve 97% correct detection rate and 95% correct classification rate on the testing set. In the future, the presented method can be further applied to passive acoustic observation applications for some other whale or dolphin species.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2019 Elsevier. This is an author produced version of a paper subsequently published in Applied Acoustics. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Electronic and Electrical Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 28 Feb 2019 15:38 |
Last Modified: | 25 Feb 2020 01:38 |
Published Version: | https://doi.org/10.1016/j.apacoust.2019.02.007 |
Status: | Published |
Publisher: | Elsevier |
Refereed: | Yes |
Identification Number: | 10.1016/j.apacoust.2019.02.007 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:143087 |
Download
Licence: CC-BY-NC-ND 4.0