Classification Of Vocalizations Of Killer Whales Using Dynamic Time
A large number of whale sounds recorded from the Captive Killer Whale Population at Marineland of Antibes, France have recently been classified into Call Types using acoustic input and visual examination of spectral patterns [1]. The repetition rate of the pulsed component of five or more examples o...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.3332 http://web.media.mit.edu/~brown/./whaleclass2waspaa.ps |
Summary: | A large number of whale sounds recorded from the Captive Killer Whale Population at Marineland of Antibes, France have recently been classified into Call Types using acoustic input and visual examination of spectral patterns [1]. The repetition rate of the pulsed component of five or more examples of each call type has been calculated using a modified form of the FFT based comb-filter method [2]. A distance matrix for these sounds was calculated using Dynamic Time Warping to compare the melodic contours. These distances were transformed into a component space using multidimensional scaling and the resulting points were clustered with a kmeans algorithm. Roughly 90 % agreement with the perceptual classification was obtained. |
---|