A pulsed-air model of blue whale B call vocalizations.

Blue whale sound production has been thought to occur by Helmholtz resonance via air flowing from the lungs into the upper respiratory spaces. This implies that the frequency of blue whale vocalizations might be directly proportional to the size of their sound-producing organs. Here we present a sound production mechanism where the fundamental and overtone frequencies of blue whale B calls can be well modeled using a series of short-duration (<1 s) wavelets. We propose that the likely source of these wavelets are pneumatic pulses caused by opening and closing of respiratory valves during air recirculation between the lungs and laryngeal sac. This vocal production model is similar to those proposed for humpback whales, where valve open/closure and vocal fold oscillation is passively driven by airflow between the lungs and upper respiratory spaces, and implies call frequencies could be actively changed by the animal to center fundamental tones at different frequency bands during the call series.

Recognizing transient low-frequency whale sounds by spectrogram correlation.

A method is described for the automatic recognition of transient animal sounds. Automatic recognition can be used in wild animal research, including studies of behavior, population, and impact of anthropogenic noise. The method described here, spectrogram correlation, is well-suited to recognition of animal sounds consisting of tones and frequency sweeps. For a sound type of interest, a two-dimensional synthetic kernel is constructed and cross-correlated with a spectrogram of a recording, producing a recognition function--the likelihood at each point in time that the sound type was present. A threshold is applied to this function to obtain discrete detection events, instants at which the sound type of interest was likely to be present. An extension of this method handles the temporal variation commonly present in animal sounds. Spectrogram correlation was compared to three other methods that have been used for automatic call recognition: matched filters, neural networks, and hidden Markov models. The test data set consisted of bowhead whale (Balaena mysticetus) end notes from songs recorded in Alaska in 1986 and 1988. The method had a success rate of about 97.5% on this problem, and the comparison indicated that it could be especially useful for detecting a call type when relatively few (5-200) instances of the call type are known.

Marine mammal call discrimination using artificial neural networks.

Recent work has applied a linear spectrogram correlator filter (SCF) to detect bowhead whale (Balaena mysticetus) song notes, outperforming both a time-series-matched filter and a hidden Markov model. The method relies on an empirical weighting matrix. An artificial neural net (ANN) may be better yet, since it offers two advantages; (i) the equivalent weighting matrix is determined by training and can converge to a more optimal solution and (ii) an ANN is a nonlinear estimator and can embody more sophisticated responses. A three-layer feed-forward ANN is ideally suited to this application and has been implemented on 1475 sounds, of which 54% were used for training and 46% kept as "unseen" test data. The trained ANN error rate was 1.5%, a twofold improvement over previous methods. It is shown that ANN hidden neurons can be interrogated to reveal the operating paradigm developed during training. The function of each of these neurons can be determined in terms of spectrographic features of the training calls. Furthermore, the operating paradigm can be controlled and training time reduced by assigning specific recognition tasks to hidden neurons prior to training, rather than initiating training with randomized weights. The ANN is compared to the SCF and the role of the "hidden" neurons and equivalent weighting matrices are discussed.