Air Traffic Controller Support by Speech Recognition

Abstract

Air traffic controllers (ATCO) are a core element of the flight guidance process. Decision support systems with accurate output data could increase the controllers’ performance or reduce their workload. Nowadays radar data based identification of controllers’ intent causes delays of up to 30 seconds. The intents could be predicted better and earlier if their spoken commands would be taken into account. Therefore, the project AcListant® combines an arrival manager (AMAN) with an automatic speech recognizer (ASR). Spoken commands are automatically recognized and forwarded to the AMAN. The AMAN updates its plan (e.g. sequence and aircraft trajectories). The ATCO also receives a direct feedback of ASR recognition performance via an (optional) visual interface. The ATCO gets better support from the assistance system without additional personal effort. This has an impact on the controller’s work and behavior like adhering closely to the radio telephony procedures and articulating more clearly. Together with the suggestion of most probable commands depending on the air traffic situation, this would lead to higher speech recognition rates and result in better AMAN assistance. Current results of a pre-study performed by the Düsseldorf Approach Area foreshadow significant positive effects of ATCO support by ASR.