Automatic classification of grouper species by their sounds using deep neural networks

Ibrahim, Ali K.; Zhuang, Hanqi; Chérubin, Laurent M.; Schärer-Umpierre, Michelle T.; Erdol, Nurgun

doi:10.1121/1.5054911

i

Automatic classification of grouper species by their sounds using deep neural networks

2018
By Ibrahim, Ali K. ; Zhuang, Hanqi ; Chérubin, Laurent M. ; ...

Details

Journal Title:

The Journal of the Acoustical Society of America
Personal Author:

Ibrahim, Ali K. ; Zhuang, Hanqi ; Chérubin, Laurent M. ; Schärer-Umpierre, Michelle T. ; Erdol, Nurgun
NOAA Program & Office:

NMFS (National Marine Fisheries Service)
Description:

In this paper, the effectiveness of deep learning for automatic classification of grouper species by their vocalizations has been investigated. In the proposed approach, wavelet denoising is used to reduce ambient ocean noise, and a deep neural network is then used to classify sounds generated by different species of groupers. Experimental results for four species of groupers show that the proposed approach achieves a classification accuracy of around 90% or above in all of the tested cases, a result that is significantly better than the one obtained by a previously reported method for automatic classification of grouper calls.
Keywords:

Acoustics And Ultrasonics Arts And Humanities (miscellaneous) Acoustics And Ultrasonics Arts And Humanities (miscellaneous) Acoustics And Ultrasonics Arts And Humanities (miscellaneous)
Source:

The Journal of the Acoustical Society of America, 144(3), EL196-EL202
DOI:

https://doi.org/10.1121/1.5054911
ISSN:

0001-4966 ; 1520-8524
Format:

PDF
Publisher:

Acoustical Society of America (ASA)
Document Type:

Journal Article
Funding:

Grant no. NA15NMF4270329
Rights Information:

Other
Compliance:

Library
Main Document Checksum:

urn:sha256:f7717a545aebda72ac9b2c0eae89732a8dd14d37ef16d7058cd93b61c653afb5
Download URL:

https://repository.library.noaa.gov/view/noaa/60258/noaa_60258_DS1.pdf
File Type:

[PDF - 1.49 MB ]

ON THIS PAGE

Details

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.