WESTWOOD─UCLA researchers have designed a wearable-tech glove that can translate American Sign Language into English speech in real-time through an APP on smartphones. The research of the glove-like device has been published in the journal Nature Electronics on Monday, June 29.
“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. In addition, we hope it can help more people learn sign language themselves,” said Jun Chen, an assistant professor of bioengineering at the UCLA Samueli School of Engineering and the principal investigator on the research.
The UCLA research team said the design of the wearable-tech glove translation system which is assisted by machine learning can solve the communication barrier between signers and non-signers. There are stretchable sensors running along each finger to detect words and phrases that have been used as American Sign Language. There is also a wireless printed circuit board on the wrist that sends the messages directly to the APP on smartphones which will later translate them into spoken language. As the sensors are sensitive, the system can offer a real-time translation swiftly.
According to the UCLA research team, as the system has analyzed 660 sign language hand gesture recognition patterns, it demonstrates a recognition rate of up to 98.63 percent and a recognition time of less than 1 second.
In comparison with the previous wearable systems that can also translate American Sign Language, the UCLA research team uses stretchable polymers as materials to design the gloves, so the wearable-tech gloves are light, flexible, and inexpensive. The UCLA research team has filed a patent.