Conference PaperPDF Available

Annotating sign language using a dedicated glyph system (the project Typannot)

Authors:
Dominique Boutet at Université de Rouen Normandie
Dominique Boutet
Patrick Doan at University of Technology of Compiègne
Patrick Doan
Claire Danet at École Supérieure d'Art et de Design d'Amiens, France
Claire Danet
  • École Supérieure d'Art et de Design d'Amiens, France
Claudia Savina Bianchini at Université de Poitiers
Claudia Savina Bianchini
Show all 6 authorsHide
Download full-text PDF
Read full-text
Download citation

Abstract

Few systems are able to annotate sign language (SL): Stokoe Notation System, HamNoSys, SignWriting, BTS. Either they are based on symbols representing SL specific parameters - difficult to write, or they are based on linear alpha-numerical arbitrary encodings. The question of annotation is widely debated and remains an essential requirement for linguistic analysis whether in the form of ID-gloss or shape description. Typannot aims at giving better typographic tools by creating a dedicated glyph system that allows users to annotate the SL parameters in an iconic way thanks to the expertise of linguists, type designers and a roboticist. We will present the concepts and the rules behind our glyphic system and show how we are able to design 237 handshapes glyphs allowing their annotation in 10 SL (based on Eccarius & Brentari 2008). The components and the rules are limited, organized in order to maximize the system economy and learning curve, both in writing and reading (Noordzij 2006). This glyphic system can annotate the other manual parameters allowing combination of handshapes, movements and location. The orientation can be deduced from information inscribed in each glyphic unit. The design of this typeface is based at least on a graphematic description of a panel of 240 signs (Bickford 2005) for 4 SL. Those three graphematic levels once unified in a common writing space should open new perspectives in researching a writing system aimed at the deaf community. This typographic system will reach a phonological level of representation in order to qualify as a viable transcription of SL. A low-cost motion capture system (Weichert et al. 2013) will be used to enrich the glyphs adding more information than just configuration, as speed, acceleration and orientation. We are also considering the latest font format (OpenType) to allow dynamic font features like contextual glyph replacement.
Content uploaded by Claudia Savina Bianchini
Author content
All content in this area was uploaded by Claudia Savina Bianchini on Aug 11, 2015
Content may be subject to copyright.
Abstracts
www.icsla2015.nl
ICSLA 2015 Abstracts
15
Annotating sign language using a dedicated glyph system (the project Typannot)
Boutet, Doan, Danet, Bianchini, Renulard & Gogueli
Few systems are able to annotate sign language (SL) : Stokoe Notation System, HamNoSys,
SignWriting, BTS. Either they are based on symbols representing SL specific parameters — difficult
to write, or they are based on linear alpha numerical arbitrary encodings. The question of annotation
is widely debated and remains an essential requirement for linguistic analysis whether in the form of
ID-gloss or shape description. Typannot aims at giving better typographic tools by creating a
dedicated glyph system that allows users to annotate the SL parameters in an iconic way thanks to
the expertise of linguists, type designers and a roboticist.
We will present the concepts and the rules behind our glyphic system and show how we are able to
design 237 handshapes glyphs allowing their annotation in 10 SL (based on Eccarius & Brentari
2008). The components and the rules are limited, organized in order to maximize the system
economy and learning curve, both in writing and reading (G. Noordzij 2006).
This glyphic system can annotate the other manual parameters allowing combination of handshapes,
movements and location. The orientation can be deduced from information inscribed in each glyphic
unit. The design of this typeface is based at least on a graphematic description of a panel of 240 signs
(Bickford 2005) for 4 SL. Those three graphematic levels once unified in a common writing space
should open new perspectives in researching a writing system aimed at the deaf community. This
typographic system will reach a phonological level of representation in order to qualify as a viable
transcription of SL.
A low-cost motion capture system (Weichert et al 2013) will be used to enrich the glyphs adding
more information than configuration as speed, acceleration and orientation. We are also considering
the latest font format (OpenType) to allow dynamic font features like contextual glyph replacement.
References
Eccarius, Petra, et Diane Brentari. « Handshape coding made easier; A theoretically based notation
for phonological transcription ». Signe Language & Linguistics 11, no 1 (2008): 69-101.
Bickford, J. Albert. The signed languages of Eastern Europe. Citeseer, 2005.
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.103.5039&rep=rep1&type=pdf.
Weichert, Frank, Daniel Bachmann, Bartholomäus Rudak, et Denis Fisseler. « Analysis of the
Accuracy and Robustness of the Leap Motion Controller ». Sensors 13, no 5 (14 mai 2013): 6380-93.
doi:10.3390/s130506380.
ResearchGate has not been able to resolve any citations for this publication.
View
Analysis of the Accuracy and Robustness of the Leap Motion Controller
Article
Full-text available
  • May 2013
  • SENSORS-BASEL
The Leap Motion Controller is a new device for hand gesture controlled user interfaces with declared sub-millimeter accuracy. However, up to this point its capabilities in real environments have not been analyzed. Therefore, this paper presents a first study of a Leap Motion Controller. The main focus of attention is on the evaluation of the accuracy and repeatability. For an appropriate evaluation, a novel experimental setup was developed making use of an industrial robot with a reference pen allowing a position accuracy of 0.2 mm. Thereby, a deviation between a desired 3D position and the average measured positions below 0.2mmhas been obtained for static setups and of 1.2mmfor dynamic setups. Using the conclusion of this analysis can improve the development of applications for the Leap Motion controller in the field of Human-Computer Interaction.
View
Handshape coding made easier A theoretically based notation for phonological transcription
Article
Full-text available
  • Dec 2008
This paper describes a notation system for the handshapes of sign languages that is theoretically motivated, grounded in empirical data, and economical in design. The system was constructed using the Prosodic Model of Sign Language Phonology. Handshapes from three lexical components — core, fingerspelling, and classifiers — were sampled from ten different sign languages resulting in a system that is relatively comprehensive and cross-linguistic. The system was designed to use only characters on a standard keyboard, which makes the system compatible with any database program. The notation is made relatively easy to learn and implement because the handshapes, along with their notations, are provided in convenient charts of photographs from which the notation can be copied. This makes the notation system quickly learnable by even inexperienced transcribers.
View
Bartholomäus Rudak, et Denis Fisseler. « Analysis of the Accuracy and Robustness of the Leap Motion Controller
  • SENSORS-BASEL
  • 6380-93
  • Frank Weichert
  • Daniel Bachmann
Weichert, Frank, Daniel Bachmann, Bartholomäus Rudak, et Denis Fisseler. « Analysis of the Accuracy and Robustness of the Leap Motion Controller ». Sensors 13, n o 5 (14 mai 2013): 6380-93. doi:10.3390/s130506380.