Vegas
10-17-2007, 07:05 PM
http://www.airforcetimes.com/news/2007/10/airforce_F35talk_71015/
Air Force pilots have become accustomed to their airplanes shouting warnings at them anytime a computer thinks they are in danger.
Soon, pilots will be talking back and the planes will listen.
Researchers at the Air Force Research Laboratory’s Human Effectiveness Directorate are working on system that enables F-35 pilots to talk with their fighters. The F-35 Lightning II will be the first U.S. fighter aircraft with speech recognition.
Researchers from the directorate’s Warfighter Interface Division are collecting data and recommending improvements to ensure the best performance when the F-35’s speech recognition system undergoes future operational tests, said David Williamson, senior crew systems engineer with over 25 years experience with speech recognition technology.
Today, pilots must press buttons, flip switches or glance at instruments for information. The new system simplifies a pilot’s workload and increases safety and efficiency, since pilots can remain focused on flying the aircraft.
To move the project from quiet labs to noisy cockpits, the team worked with six pilots at the Air Force Test Pilot School at Edwards Air Force Base, Calif., whose primary mission was flying F-16 VISTA test-bed sorties to collect speech recognition data.
Using digital recordings from in-flight tests aboard the F-16 customized for research flights, engineers pinpoint phrases that are hard for the airplane to understand and recommend alternatives that are more easily recognized. They also tweak the system’s sensitivity for speech-recognition performance with few errors.
During typical 90-minute VISTA flights, the system’s digital recorder captured the pilot’s ongoing conversation with the aircraft. Researchers then returned with the recording to the lab where they studied it for troublesome phrases and the impact of cockpit conditions, such as ambient noise or high acceleration forces, which can affect the quality of the acoustic characteristics.
If the system proves successful on the F-35, it could be applied to other platforms such as the F-22 Raptor.
The system could also be advanced enough in less than five years to enable a single ground-based controller to fly up to four unmanned aerial vehicles using voice commands supplemented with gestures or touch-panel commands.
First, the Human Effectiveness team wants the F-35 system to have an error rate of less than two percent in order to consider the baseline system ready for the initial operational test and evaluation phase.
Air Force pilots have become accustomed to their airplanes shouting warnings at them anytime a computer thinks they are in danger.
Soon, pilots will be talking back and the planes will listen.
Researchers at the Air Force Research Laboratory’s Human Effectiveness Directorate are working on system that enables F-35 pilots to talk with their fighters. The F-35 Lightning II will be the first U.S. fighter aircraft with speech recognition.
Researchers from the directorate’s Warfighter Interface Division are collecting data and recommending improvements to ensure the best performance when the F-35’s speech recognition system undergoes future operational tests, said David Williamson, senior crew systems engineer with over 25 years experience with speech recognition technology.
Today, pilots must press buttons, flip switches or glance at instruments for information. The new system simplifies a pilot’s workload and increases safety and efficiency, since pilots can remain focused on flying the aircraft.
To move the project from quiet labs to noisy cockpits, the team worked with six pilots at the Air Force Test Pilot School at Edwards Air Force Base, Calif., whose primary mission was flying F-16 VISTA test-bed sorties to collect speech recognition data.
Using digital recordings from in-flight tests aboard the F-16 customized for research flights, engineers pinpoint phrases that are hard for the airplane to understand and recommend alternatives that are more easily recognized. They also tweak the system’s sensitivity for speech-recognition performance with few errors.
During typical 90-minute VISTA flights, the system’s digital recorder captured the pilot’s ongoing conversation with the aircraft. Researchers then returned with the recording to the lab where they studied it for troublesome phrases and the impact of cockpit conditions, such as ambient noise or high acceleration forces, which can affect the quality of the acoustic characteristics.
If the system proves successful on the F-35, it could be applied to other platforms such as the F-22 Raptor.
The system could also be advanced enough in less than five years to enable a single ground-based controller to fly up to four unmanned aerial vehicles using voice commands supplemented with gestures or touch-panel commands.
First, the Human Effectiveness team wants the F-35 system to have an error rate of less than two percent in order to consider the baseline system ready for the initial operational test and evaluation phase.