Computer models for masked hearing experiments with beluga whales (Delphinapterus leucas)

Environmental assessments of manmade noise and its effects on marine mammal s need to address the question of how noise interferes with animal vocaliza tions, Seeking the answer with animal experiments is very time consuming, c ostly, and often infeasible. This article examines the possibility of estim ating results with software models. A matched filter, spectrogram cross-cor relation, critical band cross-correlation, and a back-propagation neural ne twork detected a beluga vocalization in three types of ocean noise. perform ance was compared to masked hearing experiments with a beluga whale [C. Erb e and D. M. Farmer, Deep-Sea Res. II 45, 1373-1388 (1998)]. The artificial neural network simulated the animal data most closely and raised confidence in its ability to predict the interference of a variety of noise sources w ith a variety of vocalizations. (C) 1999 Acoustical Society of America. [S0 001-4466(99)00905-4].