Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings
cs.LG, cs.SD, eess.AS
Submitted: 2026-01-13
Updated: 2026-09-22
Journal ref: Ecological Informatics, 95, 2026, 103709
DOI: 10.1016/j.ecoinf.2026.103709
License: http://creativecommons.org/licenses/by/4.0/
The gist: Even though the ocean covers the majority of the planet's surface, it remains the least explored ecosystem.
Terminology
Abstract
Even though the ocean covers the majority of the planet's surface, it remains the least explored ecosystem. As light and radio waves do not propagate through water, underwater acoustics is the main choice for various ocean applications ranging from marine biology to pollution monitoring. Increasing levels of anthropogenic noise from ships contribute significantly to underwater sound pollution, posing risks to marine ecosystems. This makes monitoring crucial to understand and quantify the impact of the ship radiated noise. Passive Acoustic Monitoring (PAM) systems are widely deployed for this purpose, generating years of underwater recordings across diverse soundscapes. Manual analysis of such large-scale data is impractical, motivating the need for automated approaches based on machine learning. Recent advances in automatic Underwater Acoustic Target Recognition (UATR) have largely relied on supervised learning, which is constrained by the scarcity of labeled data. Transfer Learning (TL) offers a promising alternative to mitigate this limitation. In this work, we conduct the first empirical comparative study of transfer learning for UATR, evaluating multiple pretrained audio models originating from diverse audio domains. The pretrained model weights are frozen, and the resulting embeddings are analyzed through classification, clustering, and similarity-based evaluations. The analysis shows that the geometrical structure of the embedding space is largely dominated by recording-specific characteristics. However, a simple linear probe can effectively suppress this recording-specific information and isolate ship-type features from these embeddings. As a result, linear probing enables effective automatic UATR using pretrained audio models at low computational cost, significantly reducing the need for a large amounts of high-quality labeled ship recordings.
Sources
- Foundation Models for Bioacoustics -- a Comparative Review
- Can Masked Autoencoders Also Listen to Birds?
- Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors
- SUPERB: Speech processing Universal PERformance Benchmark
- AVEX: What Matters for Animal Vocalization Encoding
- BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics
- animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
- BEATs: Audio Pre-Training with Acoustic Tokenizers
- BEiT: BERT Pre-Training of Image Transformers
- XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
- Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics
- Perch 2.0: The Bittern Lesson for Bioacoustics
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks