logo Idiap Research Institute        
 [BibTeX] [Marc21]
Automatic Speech Recognition and Understanding for Radar Label Maintenance Support Increases Safety and Reduces Air Traffic Controllers? Workload
Type of publication: Conference paper
Citation: Helmke_ATM2023_2023
Publication status: Published
Booktitle: Fifteenth USA/Europe Air Traffic Management Research and Development Seminar (ATM2023)
Year: 2023
Month: May
Location: Savannah, Georgia, USA
Organization: Eurocontrol (Europe), FAA (U.S.)
URL: https://www.atmseminar.org/upc...
Abstract: Air traffic controllers (ATCos) from Austro Control together with DLR quantified the benefits of automatic speech recognition and understanding (ASRU) on workload and flight safety. As the baseline procedure, ATCos enter all clearances manually (by mouse) into the aircraft radar labels. As part of our proposed solution, the ATCos are supported by ASRU, which is capable of delivering the required inputs automatically. The ATCos are only prompted to make corrections, when ASRU provided incorrect output. Overall amount of time required for manually inserting clearances, i.e., by clicking and selecting the correct input on the screen, reduced from 12,800 seconds during 14 hours of simulations time down to 405 seconds, when ATCos were supported by ASRU. A reduction of radar label maintenance time through ASRU might not be surprising given earlier experiments. However, a factor greater than 30 outperforms earlier findings. In addition, this paper also considers safety aspects, i.e., how often ATCos support provided an incorrect input into the aircraft radar labels with and without ASRU. This paper shows that ASRU systems based on artificial intelligence are reliable enough for their integration into air traffic control operations rooms.
Keywords: air traffic controller’s workload, Artificial intelligence, Automatic Speech Recognition, automatic speech understanding, human factors, saftety, situation awareness
Projects Idiap
Authors Helmke, Hartmut
Kleinert, Matthias
Ahrenhold, Nils
Ehr, heiko
Mühlhausen, Thorsten
Ohneiser, Oliver
Motlicek, Petr
Prasad, Amrutha
Juan, Zuluaga-Gomez.
Klamert, Lucas
Dokic, Jelena
Pinska Chauvin, Ella
Added by: [UNK]
Total mark: 0
Attachments
  • Helmke_ATM2023_2023.pdf
Notes