Researchers Develop A Sensor That May Actually Help Siri Hear You In A Crowded Room – Without Screaming

iPhone users are familiar with the Siri struggle — having to hold the phone’s speaker directly to your mouth to ensure she accurately translates the words spoken, especially if there’s any background noise.

Duke University researchers have developed an acoustic sensor that may be able to solve this problem by helping computers separate overlapping sounds.

The sensor uses metamaterials and compressive sensing to determine the direction of a sound and extract it from the surrounding background noise.

The prototype sensor is tested in a sound-dampening room. (Image Credit: Steve Cummer, Duke University)
The prototype sensor is tested in a sound-dampening room. (Image Credit: Steve Cummer, Duke University)

“We’ve invented a sensing system that can efficiently, reliably and inexpensively solve an interesting problem that modern technology has to deal with on a daily basis,” said Abel Xie, a PhD student in electrical and computer engineering at Duke and lead author of the paper. “We think this could improve the performance of voice-activated devices like smart phones and game consoles while also reducing the complexity of the system.”

The developed prototype is currently six inches wide, doesn’t contain any electric or moving parts, and  looks like a thick, plastic, honeycomb (or pre-sliced cheesecake) whose openings actually consist of different depths.

“The cavities behave like soda bottles when you blow across their tops,” said Steve Cummer, professor of electrical and computer engineering at Duke. “The amount of soda left in the bottle, or the depth of the cavities in our case, affects the pitch of the sound they make, and this changes the incoming sound in a subtle but detectable way.”

The team tested the device by sending three identical sounds at the sensor from three different directions. According to the results, it was able to tell them apart with a 96.7% accuracy rate.

The next step is to miniaturize the device. Once successfully smaller, the device could be used in voice-command electronics, not just Siri, as well as medical sensing devices that employ waves such as hearing aids and cochlear implants. implants.

Leave A Reply

Your email address will not be published.