Methods for automatically analyzing humpback song units
This paper presents mathematical techniques for automatically extracting and analyzing bioacoustic signals. Automatic techniques are described for isolation of target signals from background noise, extraction of features from target signals and unsupervised classification (clustering) of the target...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
2008
|
Subjects: | |
Online Access: | http://hdl.handle.net/10453/9314 |
id |
ftunivtsydney:oai:opus.lib.uts.edu.au:10453/9314 |
---|---|
record_format |
openpolar |
spelling |
ftunivtsydney:oai:opus.lib.uts.edu.au:10453/9314 2023-05-15T17:10:49+02:00 Methods for automatically analyzing humpback song units Rickwood, P Taylor, A 2008-03-19 application/pdf http://hdl.handle.net/10453/9314 unknown Journal of the Acoustical Society of America 10.1121/1.2836748 Journal of the Acoustical Society of America, 2008, 123 (3), pp. 1763 - 1772 0001-4966 http://hdl.handle.net/10453/9314 Acoustics Animals Birds Animal Communication Noise Mathematics Automatic Data Processing Signal Detection Psychological Electronic Data Processing Journal Article 2008 ftunivtsydney 2022-03-13T13:57:24Z This paper presents mathematical techniques for automatically extracting and analyzing bioacoustic signals. Automatic techniques are described for isolation of target signals from background noise, extraction of features from target signals and unsupervised classification (clustering) of the target signals based on these features. The only user-provided inputs, other than raw sound, is an initial set of signal processing and control parameters. Of particular note is that the number of signal categories is determined automatically. The techniques, applied to hydrophone recordings of humpback whales (Megaptera novaeangliae), produce promising initial results, suggesting that they may be of use in automated analysis of not only humpbacks, but possibly also in other bioacoustic settings where automated analysis is desirable. © 2008 Acoustical Society of America. Article in Journal/Newspaper Megaptera novaeangliae University of Technology Sydney: OPUS - Open Publications of UTS Scholars |
institution |
Open Polar |
collection |
University of Technology Sydney: OPUS - Open Publications of UTS Scholars |
op_collection_id |
ftunivtsydney |
language |
unknown |
topic |
Acoustics Animals Birds Animal Communication Noise Mathematics Automatic Data Processing Signal Detection Psychological Electronic Data Processing |
spellingShingle |
Acoustics Animals Birds Animal Communication Noise Mathematics Automatic Data Processing Signal Detection Psychological Electronic Data Processing Rickwood, P Taylor, A Methods for automatically analyzing humpback song units |
topic_facet |
Acoustics Animals Birds Animal Communication Noise Mathematics Automatic Data Processing Signal Detection Psychological Electronic Data Processing |
description |
This paper presents mathematical techniques for automatically extracting and analyzing bioacoustic signals. Automatic techniques are described for isolation of target signals from background noise, extraction of features from target signals and unsupervised classification (clustering) of the target signals based on these features. The only user-provided inputs, other than raw sound, is an initial set of signal processing and control parameters. Of particular note is that the number of signal categories is determined automatically. The techniques, applied to hydrophone recordings of humpback whales (Megaptera novaeangliae), produce promising initial results, suggesting that they may be of use in automated analysis of not only humpbacks, but possibly also in other bioacoustic settings where automated analysis is desirable. © 2008 Acoustical Society of America. |
format |
Article in Journal/Newspaper |
author |
Rickwood, P Taylor, A |
author_facet |
Rickwood, P Taylor, A |
author_sort |
Rickwood, P |
title |
Methods for automatically analyzing humpback song units |
title_short |
Methods for automatically analyzing humpback song units |
title_full |
Methods for automatically analyzing humpback song units |
title_fullStr |
Methods for automatically analyzing humpback song units |
title_full_unstemmed |
Methods for automatically analyzing humpback song units |
title_sort |
methods for automatically analyzing humpback song units |
publishDate |
2008 |
url |
http://hdl.handle.net/10453/9314 |
genre |
Megaptera novaeangliae |
genre_facet |
Megaptera novaeangliae |
op_relation |
Journal of the Acoustical Society of America 10.1121/1.2836748 Journal of the Acoustical Society of America, 2008, 123 (3), pp. 1763 - 1772 0001-4966 http://hdl.handle.net/10453/9314 |
_version_ |
1766067479045472256 |