Skip to main content
European Commission logo
English English
CORDIS - EU research results
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary
Content archived on 2024-05-24

Virtual Signing: Capture, Animation, Storage & Transmission

Objective

ViSiCAST will develop and evaluate Virtual Humans generating European deaf sign languages. ViSiCAST builds on SignAnim, which received two UK Royal Television Society awards for technical innovation in 1998. An English language analysis or speech recognition system drives a virtual human using data captured directly from human signers. SignAnim demonstrated that a virtual human is a valid alternative to video and could run semi-automatically. ViSiCAST will extend this work in three areas:
(1) In television. Sub-titles help hard-of-hearing people who can read easily. The virtual signer will improve access for those who sign as a first language.
(2) For Web and multi-media. Improved control over signed multi-media generation and delivery will increase the independence of deaf people using the Internet for communication and learning.
(3) In face-to-face transactions. It will improve communication between a deaf customer and a service provider.

DESCRIPTION OF WORK
A key result in the first year will be a live signing system for television using a virtual human according to a new standard transmission format, trials of face-to-face communication with deaf subjects and initial web-based tools. In the second year the project will deliver an ambitious prototype text-to-signing tool and an avatar driven from HamNoSys. Key third year results include a face-to-face dialogue system, and a semi-automatic translator from text to signing implemented within a web browser. A key result in year 1 will be live a signing system for TV using a virtual human according to a new standard transmission format, trials of face-to-face communication with deaf subjects and initial web-based tools. Year 2 will deliver an ambitious prototype text-to-signing tool and an avatar driven from HamNoSys. Key year 3 results include a face-to-face dialogue system, a semi-automatic translator from text to signing implemented within a web browser.

Call for proposal

Data not available

Coordinator

INDEPENDENT TELEVISION COMMISSION
EU contribution
No data
Address
KINGS WORTHY COURT, KINGS WORTHY
SO23 7QA WINCHESTER
United Kingdom

See on map

Total cost
No data

Participants (8)