A Translator for a Language You Cannot Speak or Write
summary
A presentation explains building a translator for a language that cannot be spoken or written, using Russian Sign Language (RSL) as the example and arguing that RSL is more than mere gestures. It covers the problem of interpreting a visual-gestural language and approaches to creating a translator system for it.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 1:09Motivation and problem
- 9:01Russian sign language theory
- 14:24Dataset collection for RSL
- 20:43Model selection for training
- 26:47Results and achievements
- 30:46Sflow model family
- 33:52Q&A
related talks
47mRGS: A Possible Writing System for LIS for Severe Communication Disabilities?
01mEnabling Real-time Sign Language Translation on Mobile Platforms with On-board Depth Cameras
51mReading Luxembourgish on the fly
08mIndian Sign Language Recognition (ISLAR)
44mDesigning for deaf people, for everyone actually
51mSign Language as a Catalyst for Inclusive Language Education
27mIndian Sign Language Recognition(ISLAR)
27mRight-to-Left, Left-to-Right: Rethinking Multilingual Design