Significant effort has been made over the last few decades to develop automated passive acoustic monitoring (PAM) systems capable of classifying cetaceans at the species level; however, these systems often require tuning when deployed in different environments. Anecdotal evidence suggests that this requirement to adjust a PAM system’s parameters is partially due to differences in the propagation characteristics. The environment-dependent propagation characteristics create variation in how a cetacean vocalization is distorted after it is emitted. If this is not accounted for, it could reduce the accuracy and precision of automated PAM systems. An aural classifier developed at Defence R&D Canada (DRDC) has successfully been used for inter-species discrimination of cetaceans. It achieves accurate results by using perceptual signal features that model the features employed by the human auditory system. To quantify the impacts of propagation on the perceptual features, an experiment was conducted in which bowhead and humpback whale vocalizations were transmitted over 1-20 km ranges during a two-day sea trial in the Gulf of Mexico. The experimental results will be presented and strategies will be discussed for training the classifier so that it is capable of operating in numerous acoustic environments with minimal adjustment of the classifier’s parameters.
