WhaleNet: a Novel Deep Learning Architecture for Marine Mammals Vocalizations on Watkins Marine Mammal Sound Database

TL;DR

WhaleNet is a new deep learning ensemble architecture that combines wavelet scattering and Mel spectrogram features to classify marine mammal vocalizations with high accuracy, improving over previous methods.

Contribution

The paper introduces WhaleNet, a novel deep ensemble model that effectively integrates WST and Mel spectrogram features for marine mammal vocalization classification.

Findings

Achieved 97.61% classification accuracy.

Improved accuracy by 8-10% over existing architectures.

Validated effectiveness of combined WST and Mel features.

Abstract

Marine mammal communication is a complex field, hindered by the diversity of vocalizations and environmental factors. The Watkins Marine Mammal Sound Database (WMMD) constitutes a comprehensive labeled dataset employed in machine learning applications. Nevertheless, the methodologies for data preparation, preprocessing, and classification documented in the literature exhibit considerable variability and are typically not applied to the dataset in its entirety. This study initially undertakes a concise review of the state-of-the-art benchmarks pertaining to the dataset, with a particular focus on clarifying data preparation and preprocessing techniques. Subsequently, we explore the utilization of the Wavelet Scattering Transform (WST) and Mel spectrogram as preprocessing mechanisms for feature extraction. In this paper, we introduce \textbf{WhaleNet} (Wavelet Highly Adaptive Learning Ensemble Network), a sophisticated deep ensemble architecture for the classification of marine mammal vocalizations, leveraging both WST and Mel spectrogram for enhanced feature discrimination. By integrating the insights derived from WST and Mel representations, we achieved an improvement in classification accuracy by $8-10\%$ over existing architectures, corresponding to a classification accuracy of $97.61\%$.