Modeling Transcribed Language Between Pilots and Air Tra c Controllers Using Long Short-Term Memory Networks
Keywords
No Thumbnail Available
Authors
Issue Date
2020-07-15
Language
en
Document type
Journal Title
Journal ISSN
Volume Title
Publisher
Title
ISSN
Volume
Issue
Startpage
Endpage
DOI
Abstract
As aviation grows, so does the desire for automating its processes. One of
the most important factors for safe and successful aviation is the communication
between pilots and air tra c controllers. This research tries to aid
in building the foundation of automating communication by developing language
models based on transcribed communication between pilots and air
tra c controllers. The aim of the paper is to nd out how suitable Long
Short-Term Memory neural networks are for modeling the communication
between the pilots and air tra c controllers, compared to more traditional
language modeling techniques. The results of the research show that Long
Short-Term Memory neural networks are suitable for modeling the communication
between pilots and air tra c controllers. However, further research
is needed to develop a more optimized model compared to the model created
in this paper, for it to take o in aviation.
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen