Detection and characterization of marine mammal calls by parametric modelling

A.T. Johansson, P.R. White


In this paper, we describe a parametric modeling method for detection and characterization of tonal signals and its application to marine mammal calls. The method tracks dominant frequencies with an adaptive notch filter (ANF), and couples this to a novel, simultaneous detection step. The detection statistic is derived from a measure of tracking reliability, obtained as a by-product of the tracking algorithm. Detection therefore comes at little extra computational cost from an algorithm that is fast, simple, and capable of dealing with multiple signals in low signal-to-noise ratios. Frequency estimates are derived directly from the time domain waveform, avoiding the resolution trade-off and other short-comings of the commonly used spectrogram. The performance of the algorithm is demonstrated on both simulated signals and recordings of right whale calls. The method is found to be noise robust and capable of extracting right whale and other calls with a low false alarm rate.


Algorithms; Computer simulation; Costs; Fish detectors; Frequencies; Mathematical models; Notch filters; Parameter estimation; Reliability; Signal systems; Signal to noise ratio; Time domain analysis; Waveform analysis; Adaptive notch filter (ANF); Marine mammals; Parametric modeling; Passive acoustic detection

Full Text:



  • There are currently no refbacks.