Have you ever tried to hold a conversation with someone in a really noisy environment? It’s hard.
But maybe not for much longer.
Researchers at the University of Washington have developed artificial intelligence technology that allows someone to hone-in on just one voice even when there is lots of other noise.
The headphone-based system requires the user to look at someone speaking for three to five seconds and this “enrols” them in a conversation and cancels out everything else.
“To use the system, a person wearing off-the-shelf headphones fitted with microphones taps a button while directing their head at someone talking,” the research report says.
“The sound waves from that speaker’s voice then should reach the microphones on both sides of the headset simultaneously.
“The headphones send that signal to an on-board embedded computer where the team’s machine learning software learns the desired speaker’s vocal patterns.
“The system latches onto that speaker’s voice and continues to play it back to the listener, even as the pair moves around.”
The findings were presented at the ACM CHI Conference on Human Factors in Computing Systems last week.
More information is available on the University of Washington website.
