Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture

Abstract The use of autonomous recordings of animal sounds to detect species is a popular conservation tool, constantly improving in fidelity as audio hardware and software evolves. Current classification algorithms utilise sound features extracted from the recording rather than the sound itself, wi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Francisco J. Bravo Sanchez, Md Rahat Hossain, Nathan B. English, Steven T. Moore
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/23f605b6d563417a98be4ee8c32ec918
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:23f605b6d563417a98be4ee8c32ec918
record_format	dspace
spelling	oai:doaj.org-article:23f605b6d563417a98be4ee8c32ec9182021-12-02T14:53:35ZBioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture10.1038/s41598-021-95076-62045-2322https://doaj.org/article/23f605b6d563417a98be4ee8c32ec9182021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95076-6https://doaj.org/toc/2045-2322Abstract The use of autonomous recordings of animal sounds to detect species is a popular conservation tool, constantly improving in fidelity as audio hardware and software evolves. Current classification algorithms utilise sound features extracted from the recording rather than the sound itself, with varying degrees of success. Neural networks that learn directly from the raw sound waveforms have been implemented in human speech recognition but the requirements of detailed labelled data have limited their use in bioacoustics. Here we test SincNet, an efficient neural network architecture that learns from the raw waveform using sinc-based filters. Results using an off-the-shelf implementation of SincNet on a publicly available bird sound dataset (NIPS4Bplus) show that the neural network rapidly converged reaching accuracies of over 65% with limited data. Their performance is comparable with traditional methods after hyperparameter tuning but they are more efficient. Learning directly from the raw waveform allows the algorithm to select automatically those elements of the sound that are best suited for the task, bypassing the onerous task of selecting feature extraction techniques and reducing possible biases. We use publicly released code and datasets to encourage others to replicate our results and to apply SincNet to their own datasets; and we review possible enhancements in the hope that algorithms that learn from the raw waveform will become useful bioacoustic tools.Francisco J. Bravo SanchezMd Rahat HossainNathan B. EnglishSteven T. MooreNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Francisco J. Bravo Sanchez Md Rahat Hossain Nathan B. English Steven T. Moore Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
description	Abstract The use of autonomous recordings of animal sounds to detect species is a popular conservation tool, constantly improving in fidelity as audio hardware and software evolves. Current classification algorithms utilise sound features extracted from the recording rather than the sound itself, with varying degrees of success. Neural networks that learn directly from the raw sound waveforms have been implemented in human speech recognition but the requirements of detailed labelled data have limited their use in bioacoustics. Here we test SincNet, an efficient neural network architecture that learns from the raw waveform using sinc-based filters. Results using an off-the-shelf implementation of SincNet on a publicly available bird sound dataset (NIPS4Bplus) show that the neural network rapidly converged reaching accuracies of over 65% with limited data. Their performance is comparable with traditional methods after hyperparameter tuning but they are more efficient. Learning directly from the raw waveform allows the algorithm to select automatically those elements of the sound that are best suited for the task, bypassing the onerous task of selecting feature extraction techniques and reducing possible biases. We use publicly released code and datasets to encourage others to replicate our results and to apply SincNet to their own datasets; and we review possible enhancements in the hope that algorithms that learn from the raw waveform will become useful bioacoustic tools.
format	article
author	Francisco J. Bravo Sanchez Md Rahat Hossain Nathan B. English Steven T. Moore
author_facet	Francisco J. Bravo Sanchez Md Rahat Hossain Nathan B. English Steven T. Moore
author_sort	Francisco J. Bravo Sanchez
title	Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
title_short	Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
title_full	Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
title_fullStr	Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
title_full_unstemmed	Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
title_sort	bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/23f605b6d563417a98be4ee8c32ec918
work_keys_str_mv	AT franciscojbravosanchez bioacousticclassificationofaviancallsfromrawsoundwaveformswithanopensourcedeeplearningarchitecture AT mdrahathossain bioacousticclassificationofaviancallsfromrawsoundwaveformswithanopensourcedeeplearningarchitecture AT nathanbenglish bioacousticclassificationofaviancallsfromrawsoundwaveformswithanopensourcedeeplearningarchitecture AT steventmoore bioacousticclassificationofaviancallsfromrawsoundwaveformswithanopensourcedeeplearningarchitecture
_version_	1718389436036677632

Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture

Ejemplares similares