New smart glasses.. know the details

extend/ A researcher at Cornell University has developed sonar glasses that “hear you” without you speaking, and the glasses attachment uses microphones and tiny speakers to read spoken words aloud as you silently command it to pause or skip a music track, enter a passcode without touching your phone or work on CAD models without keyboard.

Cornell Ph.D. student Ruidong Zhang developed the system, which builds on a similar project the team created using a wireless earphone — and models before that relied on cameras. The glasses form factor removes the need to face the camera or put something in your ear, engadget reports.

“Most technologies in silent speech recognition are limited to a selection of pre-set commands and require the user to face or wear the camera, which is impractical and useless,” said Cheng Zhang, assistant professor at Cornell University of Information Sciences. “We transmit sonar to the body.”

The researchers say the system only requires a few minutes of training data (for example, reading a string of numbers) to learn the user’s speech patterns. Then, once it’s ready for action, it sends and receives sound waves across your face, sensing mouth movements while using a deep learning algorithm to analyze echo profiles in real time with up to 95% accuracy.

And the system does this while offloading data processing (wirelessly) to your smartphone, allowing the accessory to remain small and unobtrusive. The current version offers about 10 hours of battery life for the voice sensing.

In addition, no data leaves your phone, eliminating privacy concerns. “We’re very excited about this system because it really pushes the field forward in terms of performance and privacy,” said Cheng Zhang. “It’s small, low-power, and privacy-sensitive, all of which are important features for deploying new wearable technologies in the real world.”

Privacy also plays a role when looking at potential real-world uses. For example, Ruidong Zhang suggests using it to control music playback controls (without using your hands and eyes) in a quiet library or dictating a message at a loud concert where standard options might fail. Perhaps the most exciting possibility is that people with some types of speech disabilities use it to silently feed dialogue into a vocal synthesizer, which then pronounces the words out loud.

And if all goes as planned, you could get your hands on it one day. The team at Cornell’s Intelligent Computer Interfaces for Future Interactions (SciFi) Laboratory is exploring the commercialization of the technology using Cornell’s funding program. They are also looking into applications for smart glasses to track facial, eye and upper body movements. “We believe Glass will be an important personal computing platform,” Cheng Zhang said. To understand human activities in everyday environments.