A new prototype from UCLA can translate sign language using a smartphone with 98.63% accuracy. Unlike previous devices, this one is lightweight and inexpensive. (Image credit:  UCLA)

 

American Sign Language (ASL) is a difficult language to learn, but a new glove by UCLA could make things easier. Researchers have developed an inexpensive glove that translates sign language into written and spoken words on a smartphone.

 

The prototype is made up of a pair of gloves with thin, stretchable sensors that run the length of each finger. The sensors, made from electrically conducting yarns, detect hand motions and finger placements, which are turned into electrical signals. The signals then travel to a dollar coin-sized circuit board on the back of the glove, where it transmits wireless signals to the smartphone. These are then translated into text via an app that works in real-time at a rate of up to a word per second. Sensors are also placed on tester’s faces to read the facial expressions that are part of ASL.

 

While there are similar devices available, they are limited by their bulky, heavy designs or are uncomfortable to wear. UCLA’s prototype is lightweight and inexpensive, with parts costing roughly $50. There’s a chance the price may even drop if made on a larger scale. The gloves are just a prototype for now. Researchers plan to make them faster and have them understand more signs for them to be practical. But so far it looks promising. The system works in real time, can interpret 660 ASL signs with 98.63% accuracy.

 

“Our hope is that this opens up an easy way for people who use sign language to communicate directly with non-signers without needing someone else to translate for them,” said UCLA assistant professor Jun Chen.

 

UCLA has filed for a patent on the technology. If the device ever reaches the commercial stage, it could help bridge the gap between ASL and non-ASL signers.

 

 

Have a story tip? Message me at: cabe(at)element14(dot)com

http://twitter.com/Cabe_Atwell