You can consider Apple AirPods AI headphones because they use artificial intelligence for noise cancellation. However, what if we take that audiophile tech to the next level?
That is what the folks at the University of Washington (UW) achieved with its latest innovation. Its Target Speech Hearing blocks other sounds to help you hear a specific person.
READ: AirPods Pro might have “hearing aid mode”
The technology lets you hear that person even if you’re not facing them or you’re in a noisy crowd. As a result, it could drastically improve future earbuds and hearing aids.
How do these AI headphones work?
College news publication UW News reported on the Target Speech Hearing technology. Shyam Gollakota, a UW professor in the Paul G. Allen School of Computer Science & Engineering, is one of its main researchers.
“We develop AI to modify the auditory perception of anyone wearing headphones,” he said. It works by “enrolling” a specific person into the system so that it can recognize it in a crowd.
The program works with any off-the-shelf headphones with microphones, turning them into AI headphones.
The user starts by tapping a button while directing their head at someone talking. Then, the microphones will receive those sound waves signal an on-board embedded computer.
The UW team’s machine learning software will learn the specific speaker’s vocal patterns. Eventually, the system’s ability to focus on the enrolled voice improves as the speaker keeps talking.
Gollakota and his team tested the system on 21 subjects. The respondents rated the clarity of the enrolled speaker’s voice almost twice as high as unfiltered audio.
UW News admits that the TSH system has flaws. For example, it can only enroll one speaker at a time.
It cannot register one when no loud voices are coming from the same direction as the target speaker’s voice. Still, users can repeatedly enroll a speaker until voice clarity improves.
The UW team plans to expand the system to earbuds and hearing aids. Soon, it might power your next pair of AI headphones!