The ability to identify delphinid vocalizations to species in real-time would be an asset during shipboard surveys. An automated system, Real-time Odontocete Call Classification Algorithm (ROCCA), is being developed to allow real-time acoustic species identification in the field. This Matlab-based tool automatically extracts ten variables (beginning, end, minimum and maximum frequencies, duration, slope of the beginning and end sweep, number of inflection points, number of steps, and presence/absence of harmonics) from whistles selected from a real-time scrolling spectrograph (ISHMAEL). It uses classification and regression tree analysis (CART) and discriminant function analysis (DFA) to identify whistles to species. Schools are classified based on running tallies of individual whistle classifications. Overall, 46% of schools were correctly classified for seven species and one genus (Tursiops truncatus, Stenella attenuata, S. longirostris, S. coeruleoalba, Steno bredanensis, Delphinus species, Pseudorca crassidens, and Globicephala macrorhynchus), with correct classification as high as 80% for some species. If classification success can be increased, this tool will provide a method for identifying schools that are difficult to approach and observe, will allow species distribution data to be collected when visual efforts are compromised, and will reduce the time necessary for post-cruise data analysis.

Acoustic methods may improve the ability to identify cetacean species during shipboard surveys. Whistles were recorded from nine odontocete species in the eastern tropical Pacific to determine how reliably these vocalizations can be classified to species based on simple spectrographic measurements. Twelve variables were measured from each whistle (n = 908). Parametric multivariate discriminant function analysis (DFA) correctly classified 41.1% of whistles to species. Non‐parametric classification and regression tree (CART) analysis resulted in 51.4% correct classification. Striped dolphin whistles were most difficult to classify. Whistles of bottlenose dolphins, false killer whales, and pilot whales were most distinctive. Correct classification scores may be improved by adding prior probabilities that reflect species distribution to classification models, by measuring alternative whistle variables, using alternative classification techniques, and by localizing vocalizing dolphins when collecting data for classification models.

No abstract

Acoustic techniques have the potential to increase the reliability of cetacean species identification during shipboard surveys. The whistles of nine odontocete species were compared using data collected from a towed array and sonobuoys deployed during dolphin abundance surveys in the eastern tropical Pacific. Twelve variables were measured manually from spectrographic displays of each whistle (n=912). Multivariate discriminant function analysis (DFA) resulted in 49.9% of whistles being classified to the correct species. It was hypothesized that some whistles carry less species-specific information than others, therefore, groups of five whistles were averaged to reduce the effect of these ambiguous whistles. Correct classification increased to 65.4% when DFA was run on the averaged data set. A species identification decision tree that used 7 of the 12 whistle variables was constructed using nonparametric techniques (classification and regression trees) and resulted in 53.1% correct classification when applied to the original data set. Prior probabilities were added to the decision tree based on sighting rates for each species in the study area, resulting in 56.7% correct classification. The species identification decision tree provides a relatively simple acoustic method that can be used to augment conventional visual techniques.