For more information about how Halldale can add value to your marketing and promotional campaigns or to discuss event exhibitor and sponsorship opportunities, contact our team to find out more
The Americas -
holly.foster@halldale.com
Rest of World -
jeremy@halldale.com
Researchers at Embry-Riddle Aeronautical University have developed an artificial intelligence system designed to improve pilot and air traffic controller communications.
Radio communication in aviation has long faced challenges from cockpit noise, weak transmissions, and specialized jargon. To address this, the system uses automatic speech recognition to convert spoken transmissions into text. Natural language processing then standardizes terminology, formats call signs and numbers, removes filler words, and flags possible errors.
“This new tool provides an opportunity for another leap forward to help controllers and pilots have safer radio communication,” said Andrew Schneider, assistant professor in the College of Aviation and director of the Speech and Language AI Lab. Schneider collaborated with Dr. Jianhua Liu, associate professor of Electrical and Computer Engineering, whose expertise in signal processing helped reduce word error rates from 80% to less than 15%.
The system has already supported a NASA-funded project requiring transcription of flight deck communications with high background noise. “Large language models can open up whole new data sources that we can leverage to improve safety,” said Dr. Kristy Kiernan, associate director of the Boeing Center for Aviation and Aerospace Safety.
Funded by two Embry-Riddle Boeing Center grants totaling $30,000, the research began in 2023 with recordings from 12 U.S. airports. Schneider and Liu shared results at the university’s Safety Research Symposium and AI Summit.
The team is now working on real-time applications that could assist with checklist verification, detect missed calls, or serve as a smart co-pilot to prevent communication breakdowns.