This Affordable Glove Can Translate Sign Language into Speech in Real-Time

UCLA engineers have developed a wearable glove device that can translate American Sign Language into English speech in real-time.

American Sign Language, along with signing systems for other languages, is very robust and can facilitate rich communication, but that is wasted on those of us who can’t understand it. Unfortunately, not many people without a hearing-impaired person in their lives do understand sign language. That can make it tragically difficult for a deaf person to communicate with the people around them. The ideal solution would be to make sign language classes more common in schools, but that likely won’t happen anytime soon. Until it does, UCLA engineers have developed a glove that can translate American Sign Language into English speech in real-time.

This isn’t the first time a device like this has been created, but most previous attempts were bulky or expensive. In contrast, this device design is comfortable to wear and quite affordable to produce. This wearable device connects wirelessly to the user’s smartphone, which interprets finger movements and translates them into speech. The finger movements are picked up using special sensors running along each of the five fingers of the glove. Those sensors convert the flex of each finger into an electrical signal that can be read by the circuit board that sits on top of the hand.

American Sign Language can involve more than just finger movements, which is why the researchers also tested the system with additional adhesive sensors that are attached to the user’s face. One of those sensors sits between their eyebrows and two more are placed on either side of their mouth. Those can detect basic facial expressions in order to improve the results, but they aren’t necessary for basic communication. Even the prototype glove is comfortable to wear, fairly durable, and inexpensive to build, and production versions would only be better. Offsetting most of the heavy lifting, which involves machine learning to recognize finger movements, to the smartphone app helps with that. A patent has already been filed for this technology, and it will only require an expanded vocabulary in order to become a viable product.

Cameron Coward
Writer for Hackster News. Proud husband and dog dad. Maker and serial hobbyist. Check out my YouTube channel: Serial Hobbyism
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles