Here we present the components and objectives of the EU funded project DICTA-SIGN. Dicta-Sign (http://www.dictasign.eu) is a three-year research project that involves the Institute for Language and Speech Processing, the University of Hamburg, the University of East Anglia, the University of Surrey, LIMSI/CNRS, the Université Paul Sabatier, the National Technical University of Athens, and WebSourd. It aims to improve the state of web-based communication for Deaf people by allowing the use of sign language in various human-computer interaction scenarios. It researches and develops recognition and synthesis engines for signed languages, aiming at a level of detail necessary for recognizing and generating authentic signing. In this context, Dicta-Sign aims at developing several technologies demonstrated via a sign language-aware Web 2.0. Dicta-Sign supports four European sign languages: Greek. British, German, and French Sign Language and differs from previous work in that it aims to integrate tightly recognition, animation, and machine translation. All these components are informed by appropriate linguistic models from the ground up, including phonology, grammar, and non-manual features. Expected outputs of the project include:
A parallel multi-lingual corpus for four national sign languages - German, British, French and Greek (DGS, BSL, LSF and GSL respectively),
A substantial multilingual dictionary of at least 1000 signs for each represented sign language,
A continuous sign language recognition system that achieves significant improvement in terms of coverage and accuracy of sign recognition in comparison with current technology; furthermore this system will research the novel directions of multimodal sign fusion and signer adaptation,
A language generation and synthesis component, covering in detail the role of manual, non-manual and placement within signing space,
Annotation tools which incorporate these technologies providing access to the corpus and whose long term utility can be judged by the up-take by other sign language researchers,
Three bidirectional integrated prototype systems which show the utility of the system components beyond the annotation tools application,
A showcase demonstrator which exhibits how integration of the different components can support user communication needs.
@inproceedings{efthimiou:10027:sign-lang:lrec,
author = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Glauert, John and Bowden, Richard and Braffort, Annelies and Collet, Christophe and Maragos, Petros and Goudenove, Fran{\c c}ois},
title = {{DICTA-SIGN}: Sign Language Recognition, Generation and Modelling with application in Deaf Communication},
pages = {80--83},
editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam},
booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies},
maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)},
publisher = {{European Language Resources Association (ELRA)}},
address = {Valletta, Malta},
day = {22--23},
month = may,
year = {2010},
language = {english},
url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10027.pdf}
}
| Fotinea, Stavroula-Evita