Wavelet-based feature extraction with hidden Markov model classification of Antarctic blue whale sounds

Abstract

An approach for analyzing blue whale vocalizations in continuous acoustic recordings using wavelet transform (WT) algorithm as a feature extraction method is proposed in this study. The WT-based feature extraction technique offers a unique perspective on the frequency-time properties of whale vocalizations, enabling a comprehensive understanding of the complexity of non-stationary signals. The WT-based features are seamlessly adopted with a Hidden Markov Model (HMM) for efficient and accurate classification. Through extensive theoretical evaluation and comparison with conventional methods such as Principal Component Analysis (PCA) and Dynamic Mode Decomposition (DMD), the proposed approach demonstrates superior performance in accurately detecting and classifying blue whale calls from background noise. Furthermore, when benchmarked against state-of-the-art machine learning techniques such as Artificial Neural Network (ANN), Support Vector Machine (SVM), and Spectrogram Correlation Detector (SCD), the proposed WT-HMM detector exhibits the highest average accuracy, affirming its applicability for real-time scenarios. This study presents a valuable contribution to the field of marine bioacoustics, offering an effective solution for robust blue whale vocalization analysis.