Optimizing Spectrogram Resolution and Training Strategies for Real-Time Killer Whale Call Type Classification

Abstract

Automated identification of killer whale call types from continuous acoustic recordings is essential for scalable population monitoring, yet existing general-purpose frameworks such as ANIMAL-SPOT suffer from suboptimal spectrogram resolution and lack strategies tailored to the spectral-temporal characteristics of killer whale vocalizations. We identify two key limitations of the ANIMAL-SPOT framework: (1) no possibility to choose different architecture of CNN backbone, and (2) the absence of regularization and class-balancing techniques limits generalization across call types with varying abundance. To address these issues, we propose a framework that combines optimized STFT parameters (FFT size 1024, hop length 172) with label smoothing and targeted oversampling, evaluated across three CNN backbones and five segment lengths. On a dataset of 12 killer whale vocalization classes from Avacha Gulf, Russia, our best configuration (ResNet-18 with 1200 ms segments) achieves 97.1% segment-level accuracy, compared to 96.2% for the ANIMAL-SPOT baseline — a relative error reduction of 23.7%. We further present an interactive demonstration system for uploading recordings and obtaining time-resolved call-type predictions, enabling rapid analysis of passive acoustic monitoring data.