A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Segmentation of Killer Whale Vocalizations Using the Hilbert-Huang Transform
2008
EURASIP Journal on Advances in Signal Processing
The study of cetacean vocalizations is usually based on spectrogram analysis. The feature extraction is obtained from 2D methods like the edge detection algorithm. Difficulties appear when signal-to-noise ratios are weak or when more than one vocalization is simultaneously emitted. This is the case for acoustic observations in a natural environment and especially for the killer whales which swim in groups. To resolve this problem, we propose the use of the Hilbert-Huang transform. First, we
doi:10.1155/2008/245936
fatcat:zdk5bsd4bjev7fkjxfmeervgmm