Talk To The Glove

Two University of Washington students exercised their creativity in a maker space and created a pair of gloves that won them a $10,000 prize. Obviously, they weren’t just ordinary gloves. These gloves can sense American Sign Language (ASL) and convert it to speech.

The gloves sense hand motion and sends the data via Bluetooth to an external computer. Unlike other sign language translation systems, the gloves are convenient and portable. You can see a video of the gloves in action, below.

The gloves won the Lemelson-MIT student award. The computer uses a neural network-like algorithm to examine the gesture data. When it finds a match, the associated word or phrase is spoken through a speaker. We wish we had more details to share about the inner workings, but we probably haven’t seen the last of these two guys.

We have actually seen several similar gloves in the past. We’ve also seen sensor gloves used for other things like making music.

8 thoughts on “Talk To The Glove

    1. That’s usually called lip reading, but not a bad point.

      There is at least one text-to-speech for US sign; but remember that there are different sign languages for each country, and even in some countries there are different dialects (such as “Queensland” style Australian Sign Language and “Victorian” style sign language; although often similar they arose out of different schools for the deaf, and each have quirks. For instance, “Librarian” in the queensland dialect is tapping the side of your head with two fingers, like there was a hairclip there; this is because the long-term librarian at the school always wore hairclips like that.)

      1. There are _many_ regional dialects and local variants in sign language, even in relatively small countries like my own Netherlands. Because signing used to be discouraged and repressed by the schools, there was never any effort to standarize the signs until (IIRC) the 1970’s

  1. Excellent idea and execution all for a very worthy cause. Let’s hope this gets picked up all across the world and adapted for all the sign languages out there.

  2. Turns out the whole thing was actually faked. If you watch their video, what’s happening with their hands does not even slightly match what the translator is saying and they used text prediction such as when they signed an “N” or “T” it would automatically predict their names.

    Also, a huge amount of sign language comes from body language and facial expression so it would never work properly.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.