A Human–Editable Sign Language Representation Inspired by Spontaneous Productions . . . and a Writing System?

Abstract

To equip SL with software properly, we need an input system to represent and manipulate signed contents in the same way that every day software allows to process written text. Refuting the claim that video is good enough a medium to serve the purpose, we propose to build a representation that is: editable, queryable, synthesisable and user-friendly-we define those terms upfront. The issue being functionally and conceptually linked to that of writing, we study existing writing systems, namely those in use for vocal languages, those designed and proposed for SLs, and more spontaneous ways in which SL users put their language in writing. Observing each paradigm in turn, we move on to propose a new approach to satisfy our goals of integration in software. We finally open the prospect of our proposition being used outside of this restricted scope, as a writing system in itself, and compare its properties to the other writing systems presented.

Findings of the Second WMT Shared Task on Sign Language Translation (WMT-SLT23)

“…Writing systems To date, SLs have no universally accepted written form or graphical system for transcription (Pizzuto and Pietrandrea, 2001;Filhol, 2020). Several notation systems, such as HamNoSys (Hanke, 2004) or SignWriting (Sutton, 1990;Bianchini and Borgia, 2012), are used in research or teaching but are rarely adopted as a writing system in everyday life, limiting the standardisation of data collection and processing.…”

Special issue on sign language translation and avatar technology

“…The exchange of ideas across disciplines has fostered new advances in supporting the automatic portrayal of signed language. Examples include the development of portraying sign language classifiers, which are highly visual and have no easy translation into words of spoken languages [11], and the portrayal of multiple processes that occur simultaneously on a signer's face [12]. Increased efforts in involving Deaf researchers and Deaf users have resulted in better authoring tools [13] and more Deaf-friendly methods for evaluation [14].…”

A survey on the animation of signing avatars: From sign representation to utterance synthesis

“…The sequence of signs is seen as one possible form 27 in the same way as an eye blink or a headshake. In addition, 1 if timing information has been found consistently for many in- Moreover, there is ongoing work in order to associate Azee formalism with a pictogram representation to make it more 6 accessible to the deaf community and obtain a writing system 7 that can be directly interpreted and synthesized by an animation 8 system [110].…”