Honeywell Awarded U.S. Government Contract To Develop Technology That Anonymizes Speech In Real Time

Honeywell has been awarded a three-year, multi-million dollar contract by the U.S. government's Intelligence Advanced Research Projects Activity (IARPA) to develop technology to anonymize speech in real time. As part of IARPA’s Anonymous Real-Time Speech (ARTS) program, Honeywell's technology will aim to safeguard users from unintended speech signals and support real-time communication in industries such as aviation.

Honeywell is creating a system, known as Real-time Anonymization & Speech Protection (RASP), that will operate in real time as individuals speak. By anonymizing speech, RASP seeks to address the growing risk of exploitation and privacy threats with devices such as smartphones, digital assistants, televisions, and smart appliances with microphones that might be perpetually listening. It will aim to protect the speaker's identity, as well as attributes like dialect, gender, and age and dynamic traits such as fear, stress, and anger.

To develop RASP, Honeywell will lead a team that includes experts from the University of Rochester, Texas A&M University, and University of Texas-Dallas.

"With voice technology becoming commonplace in every home, office, and public space, our voices can reveal key information about our identity and emotions that may not be appropriate for others to know. Until now, no one has been able to anonymize speech in real time while also making it easy to understand," said Tor Finseth, principal investigator of RASP at Honeywell Aerospace Technologies, in a statement. "Through our RASP system, Honeywell aims to meet U.S. government requirements to protect against speaker identification tools, human listeners, and machine learning assessments. We also aim to improve anonymous speech latency, understandability, and naturalness."

The program will initially focus on the English language, followed by Spanish and other spoken languages.

Honeywell anticipates many use cases that could benefit from its RASP technology, including in aviation, where it could help reduce the language barrier between pilots, air traffic control, and autonomous systems. The new technology could convert a heavily accented speaker's dialogue into the preferred dialect for the listener.