Who hasn’t attended a company meeting where verbally things get out of hand, corporate combatants talk (or worse, yell) over one another, and you leave the meeting and head straight to your desk where hopefully two Advil await?
It’s not just meetings, although they’re well known to have different views verbalized at the same time. Water cooler conversations, open-door office chatter, or nearby phone calls on speakerphone all can add to tense – and volume-heavy – workplace experiences.
Now, University of Washington scientists are using artificial intelligence to keep co-workers from talking over one another and reducing co-workers’ communication effectiveness in office verbal engagements.
Here’s the deal.
University researchers say they’ve created a “shape-changing smart speaker, which uses self-deploying microphones to divide rooms into speech zones and track the positions of individual speakers”, according to a University of Washington statement.
The research team used its own deep-learning algorithms to run the system, which enables any user to mute either geographic areas in the workplace areas or to “split” simultaneous conversations, even if a pair of co-workers in close proximity share similar vocal tones.
The one-inch-wide microphones automatically deploy from and then return to, a charging station when they’re no longer in use.
“This allows the system to be moved between environments and set up automatically,” university researchers say. “In a conference room meeting, for instance, such a system might be deployed instead of a central microphone, allowing better control of in-room audio.”
University researchers say the technology is groundbreaking.
“If I close my eyes and there are 10 people talking in a room, I have no idea who’s saying what and where they are in the room exactly,” says co-lead author Malek Itani, a University of Washington doctoral student in the school of computer science and engineering. “That’s extremely hard for the human brain to process.”
“Until now, it’s also been difficult for technology (to fix that issue),” Itani notes. “For the first time, using what we’re calling a robotic ‘acoustic swarm,’ we’re able to track the positions of multiple people talking in a room and separate their speech.”
A Real-Life “Cone of Silence”
Segregating dual voices only a few feet away is the stuff of science fiction legend, reminiscent of the “cone of silence” made famous in Mel Brooks’ breakthrough comedic sitcom “Get Smart.”
“If I have one microphone a foot away from me, and another microphone two feet away, my voice will arrive at the microphone that’s a foot away first,” says study co-author Tuochao Chen, a UW doctoral student at UW’s computer science school. ”If someone else is closer to the microphone that’s two feet away, their voice will arrive there first.
University scientists mastered the commingling problem by developing neural networks that leverage time-delayed signals “to separate what each person is saying and track their positions in a space.”
“That way, you can have four people having two conversations and isolate any of the four voices and locate each of the voices in a room,” Chen says.
The smart speaker tackles privacy issues in, well, a smart way. Since the technology moves and shifts by voice triggers, there are no cameras involved that visually identify anyone speaking nearby. The technology offers safeguards for auditory privacy, too.
“It has the potential to actually benefit privacy, beyond what current smart speakers allow,” Itani said. “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.”
“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,” Itani adds.
The University of Washington research team published its findings on the new smart speaker in the September 21, 2023 edition of Nature Communications.
Brian O’Connell, a former Wall Street bond trader and best-selling author, is a prominent figure in the finance industry. With a substantial background as an ex-Wall Street trader, he has authored two best-selling books: ‘The 401k Millionaire’ and ‘CNBC’s Creating Wealth’, demonstrating his profound knowledge of finance and investing.
Brian is also a finance and business writer for esteemed national platforms and publications, including CNN, TheStreet.com, CBS News, The Wall Street Journal, U.S. News & World Report, Forbes, and Fox News.
