Language technology in air traffic control

Voice communication is a volatile part of Air Traffic Control (ATC). According to research, on average one miscommunication happens every hour per radio frequency where there is frequent communication such as in TRACON. ICAO puts great emphasis on improving communication in ATC. This article proposes that a language technology system (LTS) can make communication between controller and pilot more reliable and efficient, thus improving safety in aviation. An LTS can for example detect readback errors. It can also directly feed data from the voice recognizer on XML (eXtensible Markup Language) form into a flight data processing system or interact with it as we show. By interviewing air traffic controllers and studying the literature, we identified several examples of use of language technology in ATC. As an example we take a system to support controllers in their work by making the LTS give warnings when discrepancy is found in the communications between controller and pilot. This system is not meant to control the airspace autonomously. Latest advances in language technology have enabled the development of such a system. The functionality of the proposed LTS is described using scenarios and sequence diagrams. A demonstration conversational agent using Hex Technology was implemented. A Wizard of Oz usability test was administered to seven controllers. Their attitude to the agent was positive and indicates that there is reason for further research. The performance and error logs of the agent and voice server were analyzed and give guidance on further development of a fully functioning language technology system for air traffic control.