Enhancing marine mammal species classification: A feature fusion approach for whistle calls

Whistles are transient, narrowband calls of marine mammals. This transience makes using whistles for species classification challenging. The literature uses spectral features to classify whistle calls across species (e.g., common dolphin within the dolphin genus). Spectral features are limited as they may not capture nuanced temporal (e.g., zero-crossing rates) information for species classification. Toward inter-species classification, separate classifiers for individual species demand considerable effort in data collection, annotation, model training, and computation resources. To address the gap in the spectral features’ representation and intra-species classification, a novel classification model—Temporal, Spectral, and Cepstral (TSC)—BiLSTM, was investigated. This model uses feature-level fusion strategy to integrate hybrid TSC features to capture rich and complementary whistle information not evident in temporal, spectral, or cepstral features alone. The BiLSTM network then learns these fused TSC whistle representations to classify calls from beluga, dolphins, narwhal, killer, and pilot whales. The results show the proposed TSC-BiLSTM model outperforms three baseline methods (e.g., ANN (F1-score = 64%), CNN (F1-score = 74%), and LSTM (F1-score = 84%), achieving 90% accuracy, 89% precision, 87% recall, and 88% F1-score. These findings suggest TSC-BiLSTM is a valuable tool to classify species based on passive acoustic marine mammal whistle measurements. JASCO Applied Sciences is a sponsor of this work.