SoarTech Delivers Speech AI, LinGo, to US Air Force

Soar Technology (SoarTech) has delivered eight LinGo hardware packages – scalable, automated speech recognition and cognitive agent training tools – to the U.S. Air Force Warning and Control System (AWACS) Detachments 6.

SoarTech originally proposed the technology during the Air Force Life Cycle Management Center's (AFLCMC) Simulators Division and AFWERX Direct to Phase II Small Business Innovative Research (SBIR) Pitch Day in late 2020. There, SoarTech demonstrated the effectiveness of a scalable and authorable automated speech recognition (ASR) tool, LinGo, to develop a training and assessment capability for complex tactical communications.

The LinGo hardware packages provide airmen the ability to train and rehearse communication activities during phases of training that don’t typically include communications training, such as in a part-task trainer. The system includes an automatic speech recognition capability, along with integrated synthetic agents that can simulate verbal and chat-based requests. Instructors can use LinGo to accompany computer- or platform-based training exercises for targeting communication and radio tasks and skills.

“SoarTech has observed a significant gap in DoD (Department of Defense) training with respect to crew communications and radio operations,” said Brian Stensrud, SoarTech’s director of simulation. “Our LinGo system works to address that gap in an efficient and authorable way, providing our warfighters a low-stakes way to gain confidence and skills operating on the radio and other communication media.”

Since the contract award, SoarTech has worked closely with the AFLCMC and USAF Training Detachments 6 to deliver the LinGo system on time and within budget.

“We have been working with the LinGo system for a few weeks and are confident that this system provides an enormous value to our training curriculum,” said Lt. Col. Jeff Waterman, commander, Detachment 6. “We are already getting feedback from students how the LinGo system offers them better training on communication practices and gives them more confidence going into their in-flight training. And the flexibility of the system and platform could allow us to streamline our training curriculum, which would provide significant cost savings.”

LinGo is currently being piloted and evaluated to provide communication training for the AWACS’ Airborne Radio Operator (ARO) crew position at Tinker Air Force Base, Oklahoma,.

“While this system is currently used to support training for a single role, the LinGo software can easily be integrated and applied to support training for a large set of roles throughout the Air Force and DoD at large,” Stensrud confirmed.

Amanda Bond, SoarTech lead scientist, said that LinGo allows the Air Force to author their own custom standard and non-standard ASR vocabularies for integration in existing and future training systems. LinGo allows objectively measured and assessed communication, even allowing synthetic entities to react to a trainee’s commands with both a verbal response and active response within the scenario.

“This enables training to take place with one or many AWACS crew members being played by synthetic entities, providing increased flexibility for mission training while still supporting crew communication and coordination,” said Bond. “Communication is one of the six core Crew Resource Management (CRM) skills and the cockpit/CRM program requires aircrews to learn and demonstrate these skills during classroom and simulator training.”

Embracing the Air Force Lightweight Synthetic Ecosystem, LinGo expands the training utility of any part- or whole-task trainer by effectively replicating and replacing human teammates with synthetic cognitive agents, capturing trainee speech to automatically assess performance, and reducing instructor requirements.