From Human Speech to Ocean Signals: Transferring Speech Large Models for Underwater Acoustic Target Recognition

2026-01-26

AI Summary

Underwater acoustic target recognition is hindered by the scarcity of labeled data and the complexity of marine environments. To address this challenge, this work proposes the UATR-SLM framework, which, for the first time, transfers large-scale human speech foundation models to this domain. The approach leverages pretrained speech large models as acoustic encoders by directly reusing their speech feature extraction pipelines and appends a lightweight classifier, eliminating the need for training from scratch. Evaluated on the DeepShip and ShipsEar datasets, the method achieves over 99% in-domain accuracy and 96.67% cross-domain accuracy, demonstrating exceptional generalization capability and robustness to varying signal lengths. These results validate the strong transfer potential of speech foundation models for underwater acoustic tasks.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Underwater acoustic target recognition (UATR) plays a vital role in marine applications but remains challenging due to limited labeled data and the complexity of ocean environments. This paper explores a central question: can speech large models (SLMs), trained on massive human speech corpora, be effectively transferred to underwater acoustics? To investigate this, we propose UATR-SLM, a simple framework that reuses the speech feature pipeline, adapts the SLM as an acoustic encoder, and adds a lightweight classifier.Experiments on the DeepShip and ShipsEar benchmarks show that UATR-SLM achieves over 99% in-domain accuracy, maintains strong robustness across variable signal lengths, and reaches up to 96.67% accuracy in cross-domain evaluation. These results highlight the strong transferability of SLMs to UATR, establishing a promising paradigm for leveraging speech foundation models in underwater acoustics.

Problem

• Underwater acoustic target recognition
• limited labeled data
• complex ocean environments
• speech large models
• transfer learning

Innovation

• speech large models
• underwater acoustic target recognition
• transfer learning
• foundation models
• acoustic encoder