ORCA-CLEAN: A deep denoising toolkit for killer whale communication
In bioacoustics, passive acoustic monitoring of animals living in the wild, both on land and underwater, leads to large data archives characterized by a strong imbalance between recorded animal sounds and ambient noises. Bioacoustic datasets suffer extremely from such large noise-variety, caused by...
Published in: | Interspeech 2020 |
---|---|
Main Authors: | , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | http://hdl.handle.net/21.11116/0000-0007-FE01-A |
id |
ftpubman:oai:pure.mpg.de:item_3286386 |
---|---|
record_format |
openpolar |
spelling |
ftpubman:oai:pure.mpg.de:item_3286386 2023-08-27T04:10:24+02:00 ORCA-CLEAN: A deep denoising toolkit for killer whale communication Bergler, C. Schmitt, M. Maier, A. Smeele, S. Barth, V. Noth, E. 2020-10 http://hdl.handle.net/21.11116/0000-0007-FE01-A eng eng info:eu-repo/semantics/altIdentifier/doi/10.21437/Interspeech.2020-1316 http://hdl.handle.net/21.11116/0000-0007-FE01-A Interspeech 2020 info:eu-repo/semantics/conferenceObject 2020 ftpubman https://doi.org/10.21437/Interspeech.2020-1316 2023-08-02T01:27:03Z In bioacoustics, passive acoustic monitoring of animals living in the wild, both on land and underwater, leads to large data archives characterized by a strong imbalance between recorded animal sounds and ambient noises. Bioacoustic datasets suffer extremely from such large noise-variety, caused by a multitude of external influences and changing environmental conditions over years. This leads to significant deficiencies/problems concerning the analysis and interpretation of animal vocalizations by biologists and machine-learning algorithms. To counteract such huge noise diversity, it is essential to develop a denoising procedure enabling automated, efficient, and robust data enhancement. However, a fundamental problem is the lack of clean/denoised ground-truth samples. The current work is the first presenting a fully-automated deep denoising approach for bioacoustics, not requiring any clean ground-truth, together with one of the largest data archives recorded on killer whales (Orcinus Orca) – the Orchive. Therefor, an approach, originally developed for image restoration, known as Noise2Noise (N2N), was transferred to the field of bioacoustics, and extended by using automatic machine-generated binary masks as additional network attention mechanism. Besides a significant cross-domain signal enhancement, our previous results regarding supervised orca/noise segmentation and orca call type identification were outperformed by applying ORCACLEAN as additional data preprocessing/enhancement step Conference Object Killer Whale Orca Orcinus orca Killer whale Max Planck Society: MPG.PuRe Interspeech 2020 1136 1140 |
institution |
Open Polar |
collection |
Max Planck Society: MPG.PuRe |
op_collection_id |
ftpubman |
language |
English |
description |
In bioacoustics, passive acoustic monitoring of animals living in the wild, both on land and underwater, leads to large data archives characterized by a strong imbalance between recorded animal sounds and ambient noises. Bioacoustic datasets suffer extremely from such large noise-variety, caused by a multitude of external influences and changing environmental conditions over years. This leads to significant deficiencies/problems concerning the analysis and interpretation of animal vocalizations by biologists and machine-learning algorithms. To counteract such huge noise diversity, it is essential to develop a denoising procedure enabling automated, efficient, and robust data enhancement. However, a fundamental problem is the lack of clean/denoised ground-truth samples. The current work is the first presenting a fully-automated deep denoising approach for bioacoustics, not requiring any clean ground-truth, together with one of the largest data archives recorded on killer whales (Orcinus Orca) – the Orchive. Therefor, an approach, originally developed for image restoration, known as Noise2Noise (N2N), was transferred to the field of bioacoustics, and extended by using automatic machine-generated binary masks as additional network attention mechanism. Besides a significant cross-domain signal enhancement, our previous results regarding supervised orca/noise segmentation and orca call type identification were outperformed by applying ORCACLEAN as additional data preprocessing/enhancement step |
format |
Conference Object |
author |
Bergler, C. Schmitt, M. Maier, A. Smeele, S. Barth, V. Noth, E. |
spellingShingle |
Bergler, C. Schmitt, M. Maier, A. Smeele, S. Barth, V. Noth, E. ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
author_facet |
Bergler, C. Schmitt, M. Maier, A. Smeele, S. Barth, V. Noth, E. |
author_sort |
Bergler, C. |
title |
ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
title_short |
ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
title_full |
ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
title_fullStr |
ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
title_full_unstemmed |
ORCA-CLEAN: A deep denoising toolkit for killer whale communication |
title_sort |
orca-clean: a deep denoising toolkit for killer whale communication |
publishDate |
2020 |
url |
http://hdl.handle.net/21.11116/0000-0007-FE01-A |
genre |
Killer Whale Orca Orcinus orca Killer whale |
genre_facet |
Killer Whale Orca Orcinus orca Killer whale |
op_source |
Interspeech 2020 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.21437/Interspeech.2020-1316 http://hdl.handle.net/21.11116/0000-0007-FE01-A |
op_doi |
https://doi.org/10.21437/Interspeech.2020-1316 |
container_title |
Interspeech 2020 |
container_start_page |
1136 |
op_container_end_page |
1140 |
_version_ |
1775352401923932160 |