Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network

Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) method for this task. In the evaluation stage, we present 6 bi-class classification...

Full description

Bibliographic Details
Main Authors: Dorian, Cazau, Lefort, Riwal, Bonnel, Julien, Zarader, Jean-Luc, Adam, Olivier
Format: Report
Language:unknown
Published: arXiv 2017
Subjects:
Machine Learning stat.ML
Machine Learning cs.LG
Sound cs.SD
FOS Computer and information sciences
Humpback Whale
Online Access:https://dx.doi.org/10.48550/arxiv.1703.10887
https://arxiv.org/abs/1703.10887
id ftdatacite:10.48550/arxiv.1703.10887
record_format openpolar
spelling ftdatacite:10.48550/arxiv.1703.10887 2023-05-15T16:35:58+02:00 Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network Dorian, Cazau Lefort, Riwal Bonnel, Julien Zarader, Jean-Luc Adam, Olivier 2017 https://dx.doi.org/10.48550/arxiv.1703.10887 https://arxiv.org/abs/1703.10887 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Machine Learning stat.ML Machine Learning cs.LG Sound cs.SD FOS Computer and information sciences Preprint Article article CreativeWork 2017 ftdatacite https://doi.org/10.48550/arxiv.1703.10887 2022-04-01T10:52:21Z Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) method for this task. In the evaluation stage, we present 6 bi-class classification experimentations of whale sound detection against different background noise types (e.g., rain, wind). In comparison to classical FFT-based representation like spectrograms, we showed that the use of image-based pretrained CNN features brought higher performance to classify whale sounds and background noise. : arXiv admin note: text overlap with arXiv:1702.02741 by other authors Report Humpback Whale DataCite Metadata Store (German National Library of Science and Technology)
institution Open Polar
collection DataCite Metadata Store (German National Library of Science and Technology)
op_collection_id ftdatacite
language unknown
topic Machine Learning stat.ML
Machine Learning cs.LG
Sound cs.SD
FOS Computer and information sciences
spellingShingle Machine Learning stat.ML
Machine Learning cs.LG
Sound cs.SD
FOS Computer and information sciences
Dorian, Cazau
Lefort, Riwal
Bonnel, Julien
Zarader, Jean-Luc
Adam, Olivier
Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
topic_facet Machine Learning stat.ML
Machine Learning cs.LG
Sound cs.SD
FOS Computer and information sciences
description Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) method for this task. In the evaluation stage, we present 6 bi-class classification experimentations of whale sound detection against different background noise types (e.g., rain, wind). In comparison to classical FFT-based representation like spectrograms, we showed that the use of image-based pretrained CNN features brought higher performance to classify whale sounds and background noise. : arXiv admin note: text overlap with arXiv:1702.02741 by other authors
format Report
author Dorian, Cazau
Lefort, Riwal
Bonnel, Julien
Zarader, Jean-Luc
Adam, Olivier
author_facet Dorian, Cazau
Lefort, Riwal
Bonnel, Julien
Zarader, Jean-Luc
Adam, Olivier
author_sort Dorian, Cazau
title Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
title_short Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
title_full Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
title_fullStr Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
title_full_unstemmed Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
title_sort bi-class classification of humpback whale sound units against complex background noise with deep convolution neural network
publisher arXiv
publishDate 2017
url https://dx.doi.org/10.48550/arxiv.1703.10887
https://arxiv.org/abs/1703.10887
genre Humpback Whale
genre_facet Humpback Whale
op_rights arXiv.org perpetual, non-exclusive license
http://arxiv.org/licenses/nonexclusive-distrib/1.0/
op_doi https://doi.org/10.48550/arxiv.1703.10887
_version_ 1766026287902621696

Similar Items