Voice recognition-software solutions realtime ATC workstations

Speech recognition is a key component in the building of software for an air traffic controller (ATC) workstation used to support a Controller-Pilot Data Link Communications (CPDLC) system. In the early 1990's, developers relied on hardware to make speech recognition a reality. Limitations in processing power restricted users to small grammar files, limited vocabularies and lower accuracy recognition rates. Features desired by air-traffic controllers, such as the ability to use dynamic call signs and compound messages, became more feasible with the advances in technology. This paper examines the challenges and opportunities of developing voice recognition software solutions in ATC workstations using multiple dialects and accents, complex and varied grammars and terminology, accuracy, hardware restrictions, user-friendly vs. functionality and user-training procedures.