A University of Washington team has developed an AI system, “Target Speech Hearing,” which allows headphones to focus on a single speaker’s voice by looking at them for three to five seconds.
This system uses machine learning to cancel other environmental sounds and enhance the desired speaker’s voice even as the listener moves around. It was tested on 21 subjects and showed significant improvement in voice clarity.
Currently, it can enroll only one speaker at a time and works best when no other loud voices are present in the same direction. Future plans include adapting the system for earbuds and hearing aids.