People who are deaf or hard of hearing are constantly met with the challenge of communicating, since most non-deaf people don't understand sign language. But modern technology is once again offering new solutions for old issues, and this time it comes in the shape of Uni, which uses motion gesture recognition to translate sign language to audio, and spoken word to text, in real time.
According to Uni's developers, a team of deaf and hard of hearing engineers from Rochester Institute of Technology with design and programming experience in companies such as Nintendo, Microsoft, Railcomm and ZVRS, there are 370 million deaf people in the world, and they interact with another 3.7 billion people. In order to communicate with those who cannot read sign language, deaf people may have to resort to frustrating or inefficient methods like typing out notes on a smartphone or quickly scribbling thoughts with pen and paper.
"We want to open up the rest of the world to the deaf community and give them the opportunity to go about their lives with confidence and accomplish dreams that were once thought to be impossible," says Ryan Hait-Campbell, CEO and co-founder of MotionSavvy. "Uni could make the difference for a deaf person getting paid minimum wage as a retail backroom stocker to earning a six-figure salary as an investment banker."
The Uni package comprises a tablet, a case with integrated motion tracking capabilities, and a mobile app. As the user performs sign language, he or she can see themselves through a mirror image that provides live-time feedback of their signing.
The motion sensor technology is powered by LEAP motion, which captures the gestures and allows them to be converted into voice. As sign language has variations, Smart Recognition allows users to train the system to recognize different gestures by adding new signs and words to the MotionSavvy Sign Language Database. This collaborative aspect of Uni will expand the database and provide more accurate translations as more users take it up.
Pressing the Listen button in the app converts the spoken reply from the hearing person into text onscreen. Currently the system works with Dell's Venue 8 Pro tablet only (supplied), but there are plans for Android and iOS compatibility.
The company has just launched a campaign on Indiegogo to further develop Uni and bring it to market. The system is expected to retail for US$499, but early bird backers can make significant savings by pledging $198 ($99 now and $99 at shipping). If all goes to plan, MotionSavvy expects to start shipping in the latter half of 2015.
The video below illustrates how the Uni system works.
Sources: MotionSavvy , Indiegogo
Though, I do wonder what the accuracy is in poor lighting conditions. Would a disco ball inadvertently cause you to offend someone?