Summary
Allen et al. seek to create a system to allow improved communication between the deaf community and the general public. To this end, they first seek to create an automated translator from the alphabetic portion of American Sign Language to written and spoken letters. They use an 18 sensor CyberGlove to measure the position and orientation of the users fingers and the orientation of the hand with respect to the rest of the arm. They trained a perceptron-based neural network to translate a single person's signs. With ten examples of each letter, they achieved a 90% accuracy rate for translation for a single user.
Discussion
Not much to say about this one. It's essentially CyberGlove + neural network = translator. It's a good first step, but faces a few problems, starting with the hardware being somewhat expensive. Training to a specific user isn't too big of a problem, since it could be marketed to an individual user, but a version that achieves high accuracy for multiple users would be nice.
Reference
Subscribe to:
Post Comments (Atom)
3 comments:
I agree that a version able to recognize more than one user would be nice, especially given the motivation they suggested in the paper. If the goal is to help facilitate communication between deaf and hearing communities, how would it be used? It might be useful even with the current setup for one person to own a glove and have their ASL speech translated to standard English, if they carry around some speakerphone type device to hook up as needed. But it might be valuable in other contexts to have a translator device on hand that's less user-specific, such as at conferences, airports, or other large gatherings of a unpredictable variety of people where it may be easier to acquire or keep a computerized version than a human interpreter, especially if the technology were reasonably inexpensive.
yeah - short paper, not a lot to say. they definitely should have trained and tested with multiple users though.
You brought up a great point about the individual user vs. multiple users aspect. I believe that if the technology is affordable enough for many people in the deaf community, then I don't think the authors have less work to make it a feasible commercial application. But hey, it's the CyberGlove, so I'm not seeing that happen anytime soon. Katie already addressed those particular points in her blog comment.
Post a Comment