Skip to content

Research at St Andrews

Using self-organizing maps to classify humpback whale song units and quantify their similarity

Research output: Research - peer-reviewArticle

DOI

Open Access permissions

Open

Author(s)

Jenny A. Allen, Anita Murray, Michael J. Noad, Rebecca A. Dunlop, Ellen Clare Garland

School/Research organisations

Abstract

Classification of vocal signals can be undertaken using a wide variety of qualitative and quantitative techniques. Using east Australian humpback whale song from 2002-2014, a subset of vocal signals were 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 be applied across the vocalization research community to help address concerns surrounding inconsistency in manual classification.
Close

Details

Original languageEnglish
Pages (from-to)1943-1952
JournalJournal of the Acoustical Society of America
Volume142
Issue number4
DOIs
StatePublished - 10 Oct 2017

    Research areas

  • Animal communication, Sequence analysis, Neural networks, Humpback whale

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Using agent-based models to understand the role of individuals in the song evolution of humpback whales (Megaptera novaeangliae)

    Mcloughlin, M., Lamoni, L., Garland, E. C., Ingram, S., Kirke, A., Noad, M. J., Rendell, L. & Miranda, E. 2018 In : Music & Science. 1, 17 p.

    Research output: Research - peer-reviewArticle

  2. The devil is in the detail: quantifying vocal variation in a complex, multi-levelled, and rapidly evolving display

    Garland, E. C., Rendell, L., Lilley, M. S., Poole, M. M., Allen, J. & Noad, M. J. 31 Jul 2017 In : Journal of the Acoustical Society of America. 142, 1, p. 460-472 13 p.

    Research output: Research - peer-reviewArticle

  3. Humpback whale jukebox

    Garland, E. C. Jul 2017

    Research output: ResearchOther contribution

Related by journal

  1. Fin whale density and distribution estimation using acoustic bearings derived from sparse arrays

    Harris, D. V., Miksis-Olds, J. L., Vernon, J. A. & Thomas, L. 18 May 2018 In : Journal of the Acoustical Society of America. 143, 5, p. 2980-2993 14 p.

    Research output: Research - peer-reviewArticle

  2. Modelling the broadband propagation of marine mammal echolocation clicks for click-based population density estimates

    von Benda-Beckmann, A., Thomas, L. J., Tyack, P. L. & Ainslie, M. Feb 2018 In : Journal of the Acoustical Society of America. 143, 2, p. 954-967

    Research output: Research - peer-reviewArticle

  3. Last call: Passive acoustic monitoring shows continued rapid decline of critically endangered vaquita

    Thomas, L., Jaramillo-legorreta, A., Cardenas-Hinojosa, G., Nieto-Garcia, E., Rojas-Bracho, L., Ver Hoef, J. M., Moore, J., Taylor, B., Barlow, J. & Tregenza, N. Nov 2017 In : Journal of the Acoustical Society of America. 142, 5, p. EL512-EL517 6 p.

    Research output: Research - peer-reviewArticle

  4. Categorizing click trains to increase taxonomic precision in echolocation click loggers

    Palmer, K. J., Brookes, K. & Rendell, L. Aug 2017 In : Journal of the Acoustical Society of America. 142, 2, p. 863-877 15 p.

    Research output: Research - peer-reviewArticle

ID: 249711869