top of page
Air Traffic Control Simulation & Voice Recognition
Air Traffic Control Simulation & Voice Recognition

ATVoice ®

ATVoice ®

At A Glance

ATVoice® provides voice recognition control for UFA’s ATCoach® and ATTower® air traffic control simulation systems, as well as 3rd party systems, through the users’ spoken commands, adding realism, ease of use and flexibility to the simulation exercise.


The product generates the appropriate pilot feedback/responses using a Text-To-Speech system. Multiple female and male pilot voices with distinct accents are available to increase training realism. As in the operational ATC setting, the simulation user talks directly to the pilots and the pilots in turn respond.


ATVoice is built around a state of the art speech recognition system

Accepts a user’s spoken commands, provides core recognition functions, coordinates and applies valid commands to the simulation exercise and provides appropriate pilot voice responses

Responses are generated in real time based on data from the response files and the simulation application

The user can control the speech rate, volume and pronunciation of each pilot’s voice.  May be used in applications requiring voice recognition for non-native speakers of US English. UFA has developed several international Voice Models to support a variety of non-native speakers of US English accents and dialects

Includes grammar files and tools that define the allowable voice commands or phraseology recognized by the system. In ATC applications, the grammar is typically defined in accordance with FAA, ICAO or other radio-telephony requirements. UFA optimizes each grammar to further increase recognition performance.  Grammar files also include airspace specific information such as aircraft callsigns, facility names and navigational aids. ATVoice provides a mechanism, ATVgen, for dynamically adding this information to grammar files

Voice Recording / Playback: Controller / pilot input can be recorded and played back with each simulation session via ATRecord


ATVoice can be used as a means of controlling simulation applications, reducing or in some cases eliminating the need for human control via pseudo pilots or other means. The benefits of this approach are many:

Lowers operating and recurring human resource costs

Increases efficiency and throughput, particularly during high volume exercises

Trains and enforces the use of proper phraseology

Allows the user to independently train without extraneous resources

bottom of page