Digital Total - Computing & Data Science an der Universität Hamburg und in der Wissenschaftsmetropole Hamburg

marFM®, A Multilingual Automatic Speech Recognizer (ASR) for VHF-Radio Communication

40

Not scheduled

20m

Von-Melle-Park 4

Poster

Speaker

Ms Sophia Lichtenberg (Fraunhofer CML)

Description

Radio communication is a central task and safety-critical for international shipping. Despite being based on resilient and robust technology, the quality of transmitted audio signals varies depending on antenna height and prevailing weather conditions. In addition, shipping is characterized by a high degree of crew multi-nationality, so that communications over VHF radio contain a variety of different accents and dialects that further complicate the understanding of radio messages. To address these challenges in maritime communication, we have been developing a transcription solution for marine radio that automatically converts received VHF radio signals into text. We introduce marFM®, a multilingual automatic speech recognizer (ASR) for maritime radio communication.

Keywords

radio communication, deep learning, asr, maritime

Presentation materials

marFM_Poster_Digital-Total_A0.pdf