Adaptation and Optimization of Automatic Speech Recognition (ASR) for the Maritime Domain in the Field of VHF Communication

TL;DR

This paper presents a multilingual ASR system tailored for maritime VHF communication, addressing unique challenges and demonstrating its effectiveness through analysis and evaluation on maritime radio data.

Contribution

It introduces a novel deep learning-based ASR architecture specifically designed for maritime VHF radio signals, improving transcription accuracy in this domain.

Findings

Effective transcription of maritime VHF radio signals achieved

Deep learning architecture outperforms traditional methods

Robustness demonstrated across various maritime radio data

Abstract

This paper introduces a multilingual automatic speech recognizer (ASR) for maritime radio communi-cation that automatically converts received VHF radio signals into text. The challenges of maritime radio communication are described at first, and the deep learning architecture of marFM consisting of audio processing techniques and machine learning algorithms is presented. Subsequently, maritime radio data of interest is analyzed and then used to evaluate the transcription performance of our ASR model for various maritime radio data.