There’s nothing more irritating than going to the cinema and having a chatty person ruin the film. The same goes for the din at cacophonous restaurants that can spoil a dinner date.
But, what if you could discretely mute the people around you the same way you would on a Zoom call? No confrontations, no awkward conversations, just peace and quiet.
Soon, you may be able to do just that thanks to a breakthrough scientific discovery. A team of researchers have developed a fleet of robotic smart speakers that can silence different parts of a room.
Like a troop of robot vacuums, each an inch in diameter, the droids can be automatically deployed to specific areas in a space. Once camped in their designated “speech zone”, they can use their in-built microphones, and a corresponding algorithm, to track and isolate the voices around them. Users can even program them to highlight certain conversations, while muting others.
Once their job is done, the robots can navigate back to their charging station and power themselves back up. The team, led by researchers from the University of Washington, published their findings in the journal Nature Communications.
Currently in the prototype stage, their invention consists of seven small robots that can disperse around tables. As they leave their charger, each droid moves by using an onboard sensor to avoid collisions. They also emit a high-frequency sound, similar to the way bats navigate in the dark, to avoid falling off the edge.
Putting multiple robots to work without them bumping into each other is a tricky task. So-called robot swarms include droids that help with search and rescue, mapping inhospitable environments, grabbing groceries, and fleets of self-driving cars.
Normally, scientists have to use overhead or on-device cameras, projectors, or special surfaces when co-ordinating a team of droids. But, the researchers claim their system is the first to accurately distribute a robot swarm using only sound.
Putting them to the test in offices, living rooms, and kitchens, with groups of three to five speakers, the bots managed to discern different voices within 1.6 feet (50 cm) of each other 90 per cent of the time. They did this without any prior information about the number of people in a location.
The system was also able to process three seconds of audio in 1.82 seconds on average, making it suitable for live-streaming. But not swift enough for more real-time communications, such as video calls.
As the technology progresses, the researchers envision the robot swarms playing a bigger part in smart homes and large work meetings, where they could replace the need for a central mic and lead to less confusion over voice controls.
Eventually, the team plans to make robot speakers that can move around entire rooms — meaning that chatter-free night at the movies may not be a pipe dream after all.
While the ability to snoop on specific conversations sounds like a spy’s delight, the academics say the speakers can be a boon for privacy.
“I can say, ‘Don’t record anything around my desk,’ and our system will create a bubble three feet around me. Nothing in this bubble would be recorded,” said co-lead author Malek Itani, a UW doctoral student in the Paul G Allen School of Computer Science and Engineering.
“Or if two groups are speaking beside each other and one group is having a private conversation, while the other group is recording, one conversation can be in a mute zone, and it will remain private.”
