The computation of generalized embeddings for underwater acoustic target recognition using contrastive learning

The increasing level of sound pollution in marine environments poses an increased threat to ocean health, making it crucial to monitor underwater noise. By monitoring this noise, the sources responsible for this pollution can be mapped. Monitoring is performed by passively listening to these sounds. This generates a large amount of data records, capturing a mix of sound sources such as ship activities and marine mammal vocalizations. Although machine learning offers a promising solution for automatic sound classification, current state-of-the-art methods implement supervised learning. This requires a large amount of high-quality labeled data that is not publicly available. In contrast, a massive amount of lower-quality unlabeled data is publicly available, offering the opportunity to explore unsupervised learning techniques. This research explores this possibility by implementing an unsupervised Contrastive Learning approach. Here, a Conformer-based encoder is optimized by the so-called Variance-Invariance-Covariance Regularization loss function on these lower-quality unlabeled data and the translation to the labeled data is made. Through classification tasks involving recognizing ship types and marine mammal vocalizations, our method demonstrates the ability to produce robust and generalized embeddings. This shows the potential of unsupervised methods for various automatic underwater acoustic analysis tasks. • An application of unsupervised contrastive learning (CL) on unlabeled underwater acoustic dataset for Underwater Acoustic Target Recognition. It demonstrates a novel implementation on abundantly available unlabeled data collected from a single hydrophone for the first time. • This novel framework effectively translates unstructured acoustic data into generalized embeddings which can be used for various downstream classification tasks. • The proposed unsupervised CL framework produces robust and generalized embeddings. This creates the potential for this framework to translate to other underwater acoustic analysis tasks, such as climate change monitoring and nuclear bomb test detection.