Smart speaker tracks baby’s breathing using white noise
An innovative new system is suggesting white noise from a smart speaker can be used to monitor breathing and movement in sleeping babies. So far the prototype device can detect respiratory rates with accuracy matching standard vital sign monitors, pointing to a future where smart speakers can wirelessly monitor one’s health.
“Smart speakers are becoming more and more prevalent, and these devices already have the ability to play white noise,” says co-author on the new research, Shyam Gollakota. “If we could use this white noise feature as a contactless way to monitor infants’ hand and leg movements, breathing and crying, then the smart speaker becomes a device that can do it all, which is really exciting.”
The clever system uses white noise to detect an infant’s breathing the same way sonar technology can detect objects. Capitalizing on the broad array of microphones built into modern smart speakers, the system can track reflected white noise off an infant’s body.
“We start out by transmitting a random white noise signal. But we are generating this random signal, so we know exactly what the randomness is,” says Anran Wang, first author on the new research. “That signal goes out and reflects off the baby. Then the smart speaker’s microphones get a random signal back. Because we know the original signal, we can cancel out any randomness from that and then we’re left with only information about the motion from the baby.”
The prototype device, called BreathJunior, was first tested on an infant simulator showing the system could accurately detect respiratory rates between 20 and 60 breaths per minute. BreathJunior was then tested on babies in a neonatal intensive care unit, with the babies connected to wired respiratory monitors for comparison. Again, the system proved impressively accurate, tracking respiratory rates up to 65 breaths per minute, closely matching the rates detected by wired, hospital-grade devices.
The system is still in prototype stages, however the researchers are working on developing commercial outcomes through a startup called Sound Life Sciences. Another device presented earlier this year from the same research team demonstrated the ability of a smart speaker to monitor adults for signs of cardiac arrest while they sleep. Shyam Gollakota ambitiously envisions smart speakers in the future able to monitor an array of different health markers.
“In just a few years, we have come a long way from monitoring large motions in adults to extracting the tiny motion of a newborn infant’s breathing,” says Gollakota. “This has been possible because of algorithmic innovations as well as advances in smart speaker hardware. Looking ahead, one can envision transforming a smart speaker into a ‘medical tricorder’ that can contactlessly monitor a variety of vital signs beyond just breathing.”
The new research will be presented at Mobicom in Los Cabos, Mexico later this month.
Source: University of Washington