Smartphone accelerometers could be used to eavesdrop on phone conversations, according to University of Illinois Urbana-Champaign (UIUC) researchers.
The motion sensor can capture sound vibrations during conversations, and the researchers developed a neural network to convert that very-low-sampling-rate data into high-bandwidth signals.
UIUC's Tarek Abdelzaher said, "Human speech has a special pattern. By constraining your interpretation to that special pattern, you can guess higher frequency from low frequency. This won't work with any random sound, but for some keywords or numbers, it works fairly well."
From University of Illinois at Urbana-Champaign
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found