Automated Speech Recognition in air traffic control

Abstract

Over the past few years, the technology and performance of Automated Speech Recognition (ASR) systems has been improving steadily. This has resulted in their successful use in a number of industrial applications. Motivated by this success, a look was taken at the application of ASR to Air Traffic Control, a task whose primary means of communication is verbal. In particular, ASR, and audio playback was incorporated into an Air Traffic Control Simulation task in order to replace blip-drivers, people responsible for manually keying in verbal commands and simulating pilot responses. This was done through the use of a VOTAN VPC2000 ASR continuous speech recognition system which also possessed a digital recording capability. Parsing systems were designed that utilized the syntax of ATC commands, as defined in the controller's handbook, in order to detect and correct recognition errors. As well, techniques whereby the user could correct any recognition errors himself were included. Finally, some desirable features of ASR systems to be used in this environment were formulated based on the experience gained in the ATC simulation task and parser design. These predominantly include continuous speech recognition, a simple training procedure, and an open architecture to allow for the customization of the speech recognition to the particular task at hand required by the parser.