Gloves Translate Sign Language Into Speech
3 May 2016 at 3:10 pm
In the United States, two second-year university undergraduates have developed gloves that can translate sign language into text or speech.
Their invention, SignAloud, is a pair of gloves that can recognise hand gestures that correspond to words and phrases in American Sign Language, known as ASL.
According to the inventors, each glove contains sensors that record hand position and movement, and send data wirelessly via Bluetooth to a central computer. The computer looks at the gesture data through various sequential statistical regressions, similar to a neural network. If the data matches a gesture, then the associated word or phrase is spoken through a speaker.
The university said the students honed their prototype in the UW CoMotion MakerSpace – a campus space that offers communal tools, equipment and opportunities for students to tinker, create and innovate.
For Azodi and Pryor, that meant finding a way to translate American Sign Language into a verbal form instantaneously and in an ergonomic fashion.
“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 said.
“Our gloves are lightweight, compact and worn on the hands, but ergonomic enough to use as an everyday accessory, similar to hearing aids or contact lenses.”
Azodi said: “Our purpose for developing these gloves was to provide an easy-to-use bridge between native speakers of American Sign Language and the rest of the world.”
“The idea initially came out of our shared interest in invention and problem solving. But coupling it with our belief that communication is a fundamental human right, we set out to make it more accessible to a larger audience.”
Pryor and Azodi said that their first target audience is the deaf and hard-of-hearing community, and those interested in learning and working with American Sign Language. But the gloves could also be commercialised for use in other fields, including medical technology to monitor stroke patients during rehabilitation, gesture control and enhanced dexterity in virtual reality.
They have won a $10,000 Lemelson-MIT Student Prize for undergraduates which Pryor and Azodi said would be used to refine their invention.