Sign language-to-speech translating gloves take out Microsoft Imagine Cup 2012
By Darren Quick
July 10, 2012
Since beginning in 2003, the Microsoft Imagine Cup has tasked students the world over with developing technology aimed at solving real-world problems. In this, its 10th year, students were asked to build their project around a specific Millennium Development Goal (MDG), with the finals held this month in Sydney, Australia. The winners have just been announced and beating out teams from 75 countries to claim first place (and US$25,000) in the Software Design category was the Ukraine’s quadSquad with their EnableTalk gloves that translate sign language into speech in real time.
Aiming to extend the communication capabilities of those with hearing and speech disabilities after interacting with hearing and speech impaired athletes at their school, the quadSquad team set out to develop a way for those who know sign language to more easily communicate with those who don’t. Their solution includes a hardware component – the gloves fitted with various sensors – and a software component – which translates the hand signals into speech in real time.
Although the software was developed under Windows Phone 7, the team was forced to turn to the older Windows Mobile platform for their entry because Windows Phone 7 doesn’t provide developers access to the Bluetooth stack, which is how the gloves communicate wirelessly with a mobile device running the translation software.
The gloves themselves are fitted with an accelerometer, gyroscope, compass, and 15 flex sensors along the fingers, thumb and palm that determine the position of the glove in space. Data from the sensors is relayed to a controller on the back of the glove that is powered by a rechargeable battery. The battery can be recharged via USB, while a small solar panel also helps extend the intervals between charging. Data from the glove is then transmitted via Bluetooth to a mobile device that translates the signs into speech using the Microsoft Speech API and Bing API.
The team anticipates selling each glove for around US$200 if they can get them to mass production. If they do manage to get them to market, they would sell the system with a library of standard gestures. However, with sign language varying greatly around the world, the team says users can teach the system new gestures and modify existing ones.
Congratulations to the quadSquad team as well as the more than 350 students from 75 countries who made it to the finals of the competition.
The team's EnableTalk promo video can be viewed below.