Header

UZH-Logo

Maintenance Infos

Exploiting the full potential of JASigning to build an avatar signing train announcements


Ebling, S; Glauert, J (2013). Exploiting the full potential of JASigning to build an avatar signing train announcements. In: Third International Symposium on Sign Language Translation and Avatar Technology, Chicago, IL, USA, 18 October 2013 - 19 October 2013.

Abstract

We are building a system that translates German train announcements of the Swiss Federal Railways (Schweizerische Bundesbahnen, SBB) into Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS) in real time and displays the result via an avatar. We use the JASigning system to animate the avatar. Deliverables of the projects during which JASigning was developed are the main source of documentation for the system along with notes on the website. Not all planned features have been fully implemented: some because they are used very infrequently; others because there is insuffcient linguistic research on which to base an implementation. Our team of hearing and Deaf researchers identified the avatar functionality we needed for our project. In close collaboration with the developers of JASigning, we then found workarounds for those features that were not yet directly available in the system. Our goal for this paper is to share the solutions we found, thereby providing a use case for exploiting the full potential of JASigning. The features we required were not specific to train announcements: Among them were the extension of non-manual features over multiple signs, the addition of pauses between items of a signed list, or the introduction of stamping movements following successive identical digits and fingerspelled letters. Hence, knowledge of how to achieve their designated effects in the JASigning system can be useful to persons working with other types of sign language data as well.

Abstract

We are building a system that translates German train announcements of the Swiss Federal Railways (Schweizerische Bundesbahnen, SBB) into Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS) in real time and displays the result via an avatar. We use the JASigning system to animate the avatar. Deliverables of the projects during which JASigning was developed are the main source of documentation for the system along with notes on the website. Not all planned features have been fully implemented: some because they are used very infrequently; others because there is insuffcient linguistic research on which to base an implementation. Our team of hearing and Deaf researchers identified the avatar functionality we needed for our project. In close collaboration with the developers of JASigning, we then found workarounds for those features that were not yet directly available in the system. Our goal for this paper is to share the solutions we found, thereby providing a use case for exploiting the full potential of JASigning. The features we required were not specific to train announcements: Among them were the extension of non-manual features over multiple signs, the addition of pauses between items of a signed list, or the introduction of stamping movements following successive identical digits and fingerspelled letters. Hence, knowledge of how to achieve their designated effects in the JASigning system can be useful to persons working with other types of sign language data as well.

Statistics

Downloads

360 downloads since deposited on 02 Dec 2013
42 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:19 October 2013
Deposited On:02 Dec 2013 14:05
Last Modified:08 Dec 2017 00:15
Related URLs:http://sltat.cs.depaul.edu/

Download

Download PDF  'Exploiting the full potential of JASigning to build an avatar signing train announcements'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 1MB