Apron Controller Support by Integration of Automatic Speech Recognition with an Advanced Surface Movement Guidance and Control System

Digital assistants in air traffic control today have access to a large number of sensors that allow monitoring of traffic in the air and on the ground. Voice communication between air traffic controller and pilot, however, is not used by these assistants. Whenever the information from voice communication has to be digitized, controllers are burdened to enter the information manually. Research shows that up to one third of controllers working time is spent on these manual inputs. Assistant Based Speech Recognition (ABSR) has already shown that it can reduce the amount of manual inputs from controllers. This paper presents how a modern digital assistant, a so-called A-SMGCS, can utilize the outputs of ABSR. The combined application is installed in the complex apron simulation training environment of the Frankfurt airport. This allows on the one hand the integration of recognized controller commands into the A-SMGCS planning process. On the other hand, ABSR performance is improved through the usage of A-SMGCS information. The implemented ABSR system alone reaches Word Error Rates of 3.1% for the text recognition process, which results in a callsign recognition rate of 97.4% and a command recognition rate of 91.8%. The integration of ABSR in the A-SMGCS brings a reduction of workload for controllers, which increases the overall performance and safety.