Speech privacy continues to be a popular topic among enterprise-focused manufacturers, particularly as hybrid work continues to be the new normal. Some inventive solutions for speech privacy raise eyebrows, and a prototype solution by researchers from the University of Washington is no different.
Dubbed an “acoustic swarm” by the research team, these small robots use their microphones to navigate around a surface area, distributing themselves as widely as possible to cast an acoustic net around a given area. To achieve isolation of individual audio sources, say, a specific person speaking in a crowded cafe, a large array of microphones must pick up all the different audio sources in the area. This information is then processed together to form a spatial map of all audio sources and their relative location to one another. Only then can algorithms comb the data to generate separate streams for each source, muting all other sources to isolate the desired audio.
“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. If someone else is closer to the microphone that’s two feet away, their voice will arrive there first,” said co-lead author Tuochao Chen. “We developed neural networks that use these time-delayed signals to separate what each person is saying and track their positions in a space. So you can have four people having two conversations and isolate any of the four voices and locate each of the voices in a room.”
The prototype isn’t perfect, as there is still the issue of latency that needs to be worked out. The research team hopes that these little robots could be a portable, self-deploying solution for different applications, such as conference rooms.
“It has the potential to actually benefit privacy, beyond what current smart speakers allow,” said doctoral student Malek Itani, co-lead author on the study. “I can say, ‘Don’t record anything around my desk,’ and our system will create a bubble 3 feet (0.9 m) 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.”
The team’s research has been published in the journal Nature Communications.
