Using self-organizing maps to classify humpback whale song units and quantify their similarity
Classification of vocal signals can be undertaken using a wide variety of qualitative and quantitative techniques. Using east Australian humpback whale song from 2002 to 2014, a subset of vocal signals was acoustically measured and then classified using a Self-Organizing Map (SOM). The SOM created (...
Published in: | The Journal of the Acoustical Society of America |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
A I P Publishing
2017
|
Subjects: | |
Online Access: | https://espace.library.uq.edu.au/view/UQ:692212 |
id |
ftunivqespace:oai:espace.library.uq.edu.au:UQ:692212 |
---|---|
record_format |
openpolar |
spelling |
ftunivqespace:oai:espace.library.uq.edu.au:UQ:692212 2023-05-15T16:35:55+02:00 Using self-organizing maps to classify humpback whale song units and quantify their similarity Allen, Jenny A. Murray, Anita Noad, Michael J. Dunlop, Rebecca A. Garland, Ellen C. 2017-10-01 https://espace.library.uq.edu.au/view/UQ:692212 eng eng A I P Publishing doi:10.1121/1.4982040 issn:0001-4966 issn:1520-8524 orcid:0000-0002-2799-8320 orcid:0000-0002-0427-6317 Not set Bottle-Nosed Dolphins Megaptera-Novaeangliae Classification Vocalizations Information Repertoire Communication Animals Signals Scale 1201 Arts and Humanities (miscellaneous) 3102 Acoustics and Ultrasonics Journal Article 2017 ftunivqespace https://doi.org/10.1121/1.4982040 2020-12-08T02:23:54Z Classification of vocal signals can be undertaken using a wide variety of qualitative and quantitative techniques. Using east Australian humpback whale song from 2002 to 2014, a subset of vocal signals was acoustically measured and then classified using a Self-Organizing Map (SOM). The SOM created (1) an acoustic dictionary of units representing the song's repertoire, and (2) Cartesian distance measurements among all unit types (SOM nodes). Utilizing the SOM dictionary as a guide, additional song recordings from east Australia were rapidly (manually) transcribed. To assess the similarity in song sequences, the Cartesian distance output from the SOM was applied in Levenshtein distance similarity analyses as a weighting factor to better incorporate unit similarity in the calculation (previously a qualitative process). SOMs provide a more robust and repeatable means of categorizing acoustic signals along with a clear quantitative measurement of sound type similarity based on acoustic features. This method can be utilized for a wide variety of acoustic databases especially those containing very large datasets and can be applied across the vocalization research community to help address concerns surrounding inconsistency in manual classification. (C) 2017 Acoustical Society of America. Article in Journal/Newspaper Humpback Whale Megaptera novaeangliae The University of Queensland: UQ eSpace The Journal of the Acoustical Society of America 142 4 1943 1952 |
institution |
Open Polar |
collection |
The University of Queensland: UQ eSpace |
op_collection_id |
ftunivqespace |
language |
English |
topic |
Bottle-Nosed Dolphins Megaptera-Novaeangliae Classification Vocalizations Information Repertoire Communication Animals Signals Scale 1201 Arts and Humanities (miscellaneous) 3102 Acoustics and Ultrasonics |
spellingShingle |
Bottle-Nosed Dolphins Megaptera-Novaeangliae Classification Vocalizations Information Repertoire Communication Animals Signals Scale 1201 Arts and Humanities (miscellaneous) 3102 Acoustics and Ultrasonics Allen, Jenny A. Murray, Anita Noad, Michael J. Dunlop, Rebecca A. Garland, Ellen C. Using self-organizing maps to classify humpback whale song units and quantify their similarity |
topic_facet |
Bottle-Nosed Dolphins Megaptera-Novaeangliae Classification Vocalizations Information Repertoire Communication Animals Signals Scale 1201 Arts and Humanities (miscellaneous) 3102 Acoustics and Ultrasonics |
description |
Classification of vocal signals can be undertaken using a wide variety of qualitative and quantitative techniques. Using east Australian humpback whale song from 2002 to 2014, a subset of vocal signals was acoustically measured and then classified using a Self-Organizing Map (SOM). The SOM created (1) an acoustic dictionary of units representing the song's repertoire, and (2) Cartesian distance measurements among all unit types (SOM nodes). Utilizing the SOM dictionary as a guide, additional song recordings from east Australia were rapidly (manually) transcribed. To assess the similarity in song sequences, the Cartesian distance output from the SOM was applied in Levenshtein distance similarity analyses as a weighting factor to better incorporate unit similarity in the calculation (previously a qualitative process). SOMs provide a more robust and repeatable means of categorizing acoustic signals along with a clear quantitative measurement of sound type similarity based on acoustic features. This method can be utilized for a wide variety of acoustic databases especially those containing very large datasets and can be applied across the vocalization research community to help address concerns surrounding inconsistency in manual classification. (C) 2017 Acoustical Society of America. |
format |
Article in Journal/Newspaper |
author |
Allen, Jenny A. Murray, Anita Noad, Michael J. Dunlop, Rebecca A. Garland, Ellen C. |
author_facet |
Allen, Jenny A. Murray, Anita Noad, Michael J. Dunlop, Rebecca A. Garland, Ellen C. |
author_sort |
Allen, Jenny A. |
title |
Using self-organizing maps to classify humpback whale song units and quantify their similarity |
title_short |
Using self-organizing maps to classify humpback whale song units and quantify their similarity |
title_full |
Using self-organizing maps to classify humpback whale song units and quantify their similarity |
title_fullStr |
Using self-organizing maps to classify humpback whale song units and quantify their similarity |
title_full_unstemmed |
Using self-organizing maps to classify humpback whale song units and quantify their similarity |
title_sort |
using self-organizing maps to classify humpback whale song units and quantify their similarity |
publisher |
A I P Publishing |
publishDate |
2017 |
url |
https://espace.library.uq.edu.au/view/UQ:692212 |
genre |
Humpback Whale Megaptera novaeangliae |
genre_facet |
Humpback Whale Megaptera novaeangliae |
op_relation |
doi:10.1121/1.4982040 issn:0001-4966 issn:1520-8524 orcid:0000-0002-2799-8320 orcid:0000-0002-0427-6317 Not set |
op_doi |
https://doi.org/10.1121/1.4982040 |
container_title |
The Journal of the Acoustical Society of America |
container_volume |
142 |
container_issue |
4 |
container_start_page |
1943 |
op_container_end_page |
1952 |
_version_ |
1766026234544783360 |