Automatic detection and classification of odontocete whistles

D. Gillespie, M. Caillat, J. Gordon, P. White

Research output: Contribution to journalArticlepeer-review

97 Citations (Scopus)

Abstract

Methods for the fully automatic detection and species classification of odontocete whistles are described. The detector applies a number of noise cancellation techniques to a spectrogram of sound data and then searches for connected regions of data which rise above a pre-determined threshold. When tested on a dataset of recordings which had been carefully annotated by a human operator, the detector was able to detect (recall) 79.6% of human identified sounds that had a signal-to-noise ratio above 10 dB, with 88% of the detections being valid. A significant problem with automatic detectors is that they tend to partially detect whistles or break whistles into several parts. A classifier has been developed specifically to work with fragmented whistle detections. By accumulating statistics over many whistle fragments, correct classification rates of over 94% have been achieved for four species. The success rate is, however, heavily dependent on the number of species included in the classifier mix, with the mean correct classification rate dropping to 58.5% when 12 species were included.
Original languageEnglish
Pages (from-to)2427-2437
Number of pages11
JournalJournal of the Acoustical Society of America
Volume134
Issue number3
DOIs
Publication statusPublished - 1 Sept 2013

Fingerprint

Dive into the research topics of 'Automatic detection and classification of odontocete whistles'. Together they form a unique fingerprint.

Cite this