Loading...
Parameter-Efficient finetuning of ASR models for maritime radio communications in Ireland
Date
2026-03-22
Abstract
The need for manual logging of critical Very High Frequency (VHF) radio communi-cations by the Irish Coast Guard (IRCG) puts an additional cognitive load on watch officers, compromising their situational awareness. While Automatic Speech Recogni-tion (ASR) offers a solution, generic foundational models underperform in the maritime domain due to acoustic mismatches and a scarcity of domain-specific training data. The goal of this work is to address this gap by developing a data preparation pipeline and evaluating different parameter-efficient finetuning (PEFT) methods in a low-resource scenario. A 2-hour labelled dataset was created and used to train the OpenAI whisper-large model. The effectiveness of two PEFT techniques, namely, Encoder Freezing and Low-Rank Adaptation (LoRA) was evaluated. These finetuned models outperformed the original model’s baseline 62.8% Word Error Rate (WER). The constrained LoRA configuration proved most effective, achieving a 28.12% WER, a 52.2% relative reduc-tion in error.
Supervisor
Description
Publisher
Citation
33rd International Conference on Artificial Intelligence and Cognitive Science (AICS'25)
Collections
Files
ULRR Identifiers
Funding code
Funding Information
Sustainable Development Goals
External Link
License
Attribution-NonCommercial-ShareAlike 4.0 International