[Sw-l] Fwd: AI + machine learning to teach SLs on the web
0000001342802f5f-dmarc-request at LISTSERV.VALENCIACOLLEGE.EDU
Fri Dec 3 19:27:51 UTC 2021
December 3, 2021
Dear SW List Members:
This message was just sent to me from the Sign Language Linguists List (SLLING-L). Very interesting message about Machine learning, and sign languages.
> Begin forwarded message:
> From: Mark Mandel <markamandel at GMAIL.COM>
> Subject: AI + machine learning to teach SLs on the web
> Date: December 3, 2021 at 6:05:08 AM PST
> To: SLLING-L at LISTSERV.VALENCIACOLLEGE.EDU
> Reply-To: linguists interested in signed languages <SLLING-L at LISTSERV.VALENCIACOLLEGE.EDU>
> Machine learning to make sign language more accessible
> <https://blog.google/outreach-initiatives/accessibility/ml-making-sign-language-more-accessible/amp/ <https://blog.google/outreach-initiatives/accessibility/ml-making-sign-language-more-accessible/amp/>>
> Kemal El Moujahid
> Director, Product Management
> Published Dec 01, 2021
> Google has spent over twenty years helping to make information accessible and useful in more than 150 languages. And our work is definitely not done, because the internet changes so quickly. About 15% of searches we see are entirely new every day. And when it comes to other types of information beyond words, in many ways, technology hasn’t even begun to scratch the surface of what’s possible. Take one example: sign language.
> The task is daunting. There are as many sign languages as there are spoken languages around the world. That’s why, when we began exploring how we could better support sign language, we started small by researching and experimenting with what machine learning models could recognize. We spoke with members of the Deaf community, as well as linguistic experts, working closely with our partners at The Nippon Foundation, The Chinese University of Hong Kong and Kwansei Gakuin University. We began combining several ML models to recognize sign language as a sum of its parts — going beyond just hands to include body gestures and facial expressions.
> Advances in AI and ML now allow us to reliably detect hands, body poses and facial expressions using any camera inside a laptop or mobile phone. SignTown uses the MediaPipe Holistic model <https://google.github.io/mediapipe/solutions/holistic> to identify keypoints from raw video frames, which we then feed into a classifier model to determine which sign is the closest match. This all runs inside of the user's browser, powered by Tensorflow.js <https://www.tensorflow.org/js>.
> Click link for full article
> Mark Mandel
SIGNWRITING LIST INFORMATION
SignWriting List moderator
sutton at signwriting.org
Post Messages to the SignWriting List:
sw-l at listserv.valenciacollege.edu
SignWriting List Archives & Home Page
Join, Leave or Change How You Receive SW List Messages
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Sw-l