The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive Learning

TL;DR

This paper introduces an unsupervised contrastive learning method using a Conformer encoder to generate robust embeddings for underwater acoustic target recognition, addressing data scarcity issues in marine sound classification.

Contribution

It presents a novel application of contrastive learning with a Conformer encoder for underwater sound classification, enabling effective use of unlabeled data for generalized embeddings.

Findings

Robust embeddings achieved for ship and marine mammal sounds

Unsupervised approach reduces reliance on labeled data

Method outperforms some supervised baselines in classification

Abstract

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 to produce robust and generalized embeddings. This shows to potential of unsupervised methods for various automatic underwater acoustic analysis tasks.