Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings

Abstract Investigating the dynamics of biodiversity via passive acoustic monitoring is a challenging task, owing to the difficulty of identifying different animal vocalizations. Several indices have been proposed to measure acoustic complexity and to predict biodiversity. Although these indices perf...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tzu-Hao Lin, Shih-Hua Fang, Yu Tsao
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/444fdb5d432d46409149de5e68c9845e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:444fdb5d432d46409149de5e68c9845e
record_format	dspace
spelling	oai:doaj.org-article:444fdb5d432d46409149de5e68c9845e2021-12-02T12:30:34ZImproving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings10.1038/s41598-017-04790-72045-2322https://doaj.org/article/444fdb5d432d46409149de5e68c9845e2017-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-04790-7https://doaj.org/toc/2045-2322Abstract Investigating the dynamics of biodiversity via passive acoustic monitoring is a challenging task, owing to the difficulty of identifying different animal vocalizations. Several indices have been proposed to measure acoustic complexity and to predict biodiversity. Although these indices perform well under low-noise conditions, they may be biased when environmental and anthropogenic noises are involved. In this paper, we propose a periodicity coded non-negative matrix factorization (PC-NMF) for separating different sound sources from a spectrogram of long-term recordings. The PC-NMF first decomposes a spectrogram into two matrices: spectral basis matrix and encoding matrix. Next, on the basis of the periodicity of the encoding information, the spectral bases belonging to the same source are grouped together. Finally, distinct sources are reconstructed on the basis of the cluster of the basis matrix and the corresponding encoding information, and the noise components are then removed to facilitate more accurate monitoring of biological sounds. Our results show that the PC-NMF precisely enhances biological choruses, effectively suppressing environmental and anthropogenic noises in marine and terrestrial recordings without a need for training data. The results may improve behaviour assessment of calling animals and facilitate the investigation of the interactions between different sound sources within an ecosystem.Tzu-Hao LinShih-Hua FangYu TsaoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-10 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Tzu-Hao Lin Shih-Hua Fang Yu Tsao Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
description	Abstract Investigating the dynamics of biodiversity via passive acoustic monitoring is a challenging task, owing to the difficulty of identifying different animal vocalizations. Several indices have been proposed to measure acoustic complexity and to predict biodiversity. Although these indices perform well under low-noise conditions, they may be biased when environmental and anthropogenic noises are involved. In this paper, we propose a periodicity coded non-negative matrix factorization (PC-NMF) for separating different sound sources from a spectrogram of long-term recordings. The PC-NMF first decomposes a spectrogram into two matrices: spectral basis matrix and encoding matrix. Next, on the basis of the periodicity of the encoding information, the spectral bases belonging to the same source are grouped together. Finally, distinct sources are reconstructed on the basis of the cluster of the basis matrix and the corresponding encoding information, and the noise components are then removed to facilitate more accurate monitoring of biological sounds. Our results show that the PC-NMF precisely enhances biological choruses, effectively suppressing environmental and anthropogenic noises in marine and terrestrial recordings without a need for training data. The results may improve behaviour assessment of calling animals and facilitate the investigation of the interactions between different sound sources within an ecosystem.
format	article
author	Tzu-Hao Lin Shih-Hua Fang Yu Tsao
author_facet	Tzu-Hao Lin Shih-Hua Fang Yu Tsao
author_sort	Tzu-Hao Lin
title	Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
title_short	Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
title_full	Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
title_fullStr	Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
title_full_unstemmed	Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
title_sort	improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/444fdb5d432d46409149de5e68c9845e
work_keys_str_mv	AT tzuhaolin improvingbiodiversityassessmentviaunsupervisedseparationofbiologicalsoundsfromlongdurationrecordings AT shihhuafang improvingbiodiversityassessmentviaunsupervisedseparationofbiologicalsoundsfromlongdurationrecordings AT yutsao improvingbiodiversityassessmentviaunsupervisedseparationofbiologicalsoundsfromlongdurationrecordings
_version_	1718394329791201280

Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings

Ejemplares similares