Sensory voice and face biometric platform identifies users with masks, detects symptoms

Jun 2, 2020 | Luana Pascu

Sensory voice and face biometric platform identifies users with masks, detects symptoms

AI at the edge pioneer Sensory has upgraded its face and voice biometric fusion platform with features to help device and app developers build products for life post-COVID-19, the company announced.

Since face masks are now a general recommendation, many biometric facial recognition systems, such as those in smartphones, are no longer performing because they cannot identity a user if the face is half covered, the company points out. Since many functions require facial recognition to operate, TrulySecure now claims it can recognize users when wearing masks and detect coughs and sneezes, without jeopardizing security.

Sensory’s SDK combines face and voice biometrics to operate in difficult scenarios such as background noise or facial obstruction. The two complement each other to ensure high accuracy and a seamless, touchless user experience. The technology is trained to work with multiple enrollments where users can submit both a normal image through facial recognition and an image of them wearing a mask. While many solutions on the market block the process when a mask is detected, Sensory’s technology leverages different templates for accurate recognition through both voice and face biometrics.

“In unprecedented times like these, device manufacturers and app developers are being challenged to find new ways to keep people safe and secure,” said Todd Mozer, CEO at Sensory, in a prepared statement. “TrulySecure does just that, allowing apps and devices to recognize and authenticate users in all conditions, even when wearing masks, thus eliminating the need for people to touch their face or remove their masks when in public. But we’re taking things a step further by updating the Sound ID component of TrulySecure to recognize certain noises that can be indicative of users being sick or around people who are sick.”

Sound ID has been one of TrulySecure’s key features for the past months, according to the announcement. The company has upgraded the solution by leveraging its deep learning model training to detect coughs and sneezes, track users’ health and compile health statistics.

Earlier this year, Sensory partnered with Aiquido for a white label voice solution with biometrics and action execution for vehicles and other applications.