Although sign language has always been the communication method of choice for the the hearing-impaired, it’s something that not everyone can use. That barrier may now be a thing of the past, thanks to a couple of University of Washington students who have developed a pair of gloves that actually converts sign language into written and spoken text.
The brainchild of UW sophomores Navid Azodi and Thomas Pryor, the aptly named SignAloud gloves are capable of recognizing gestures that correspond to words and phrases in American Sign Language. The lightweight, compact accessory is equipped with what appears to be an Arduino Micro (ATmega32U4) at its core along with sensors that record hand position and movement and then send data wirelessly over Bluetooth to a central computer. The computer analyzes the gesture data through various sequential statistical regressions, similar to a neural network. If the data match a gesture, then the associated word or phrase is spoken through a speaker. Eventually, the speech will also be played back on a smartphone.
“Many of the sign language translation devices already out there are not practical for everyday use. Some use video input, while others have sensors that cover the user’s entire arm or body,” Pryor explains.
Although this may not be the first sign language translation gadget we’ve come across, it is certainly one of the most ergonomic and could easily become a part of people’s everyday lives, similar to hearing aids and contact lenses. What’s more, the project was named a recipient of the prestigious Lemelson-MIT Student Prize, a nationwide search for the most inventive undergraduate and graduate students.
Intrigued? You can see the glove in action below, and read more about SignAloud here.
[Image: University of Washington]