| Summary: | Author Posting. © Acoustical Society of America, 2009. This article is posted here by permission of Acoustical Society of America for personal use, not for redistribution. The definitive version was published in Journal of the Acoustical Society of America 126 (2009): 451-459, doi:10.1121/1.3132525. In this article, a pitch tracking algorithm [named discrete logarithmic Fourier transformation-pitch detection algorithm (DLFT-PDA)], originally designed for human telephone speech, was modified for killer whale vocalizations. The multiple frequency components of some of these vocalizations demand a spectral (rather than temporal) approach to pitch tracking. The DLFT-PDA algorithm derives reliable estimations of pitch and the temporal change of pitch from the harmonic structure of the vocal signal. Scores from both estimations are combined in a dynamic programming search to find a smooth pitch track. The algorithm is capable of tracking killer whale calls that contain simultaneous low and high frequency components and compares favorably across most signal to noise ratio ranges to the peak-picking and sidewinder algorithms that have been used for tracking killer whale vocalizations previously. C.W. was supported by DARPA under Contract No. N66001-96-C-8526, monitored through Naval Command, Control, and Ocean Surveillance Center and by the National Science Foundation under Grant No. IRI-9618731. A.D.S. was supported by a National Defense Science and Engineering Graduate Fellowship.
|
|---|