Eighth International Workshop on
Sign Language Translation and Avatar Technology

Recent research in the use of avatars to animate sign language promises to provide increased accessibility for deaf people. In addition, avatars support sign linguistics research, providing a potential target for translation from spoken and other sign languages, and scan light on human factors of sign language usage.

Submissions are invited for a full-day workshop that aims to bring together researchers who work with sign language translation with those who develop sign language avatar technologies. We invite papers on the following topics:

• Machine Learning and Multimodality
  • Mapping techniques between the visual domain and the linguistic annotations
  • Sign language annotation profiting from machine learning

• Translation Technologies
  • Use of corpora to inform translation
  • Modelling signing space for classifier construction, and constructed action
  • Incorporation of non-manual features in production
  • Emotional and prosodic aspects
• Avatar Animation
  • Requirements for signing avatar technology
  • Linguistically informed notations for gestural animation
  • Use of corpora to inform animation
  • Realistic portrayal of sign language
  • Flexibility in animation of facial gestures and mouthing
• Usability
  • Evaluation methods for sign translation systems
  • Acceptability of signing avatars
  • Editing tools for signing texts

Oral/signed presentations and posters (with or without demonstrations) have equal status, and authors are encouraged to suggest the presentation format best suited to communicate their ideas.

Papers should contain a complete description of ideas and applicable research results in a maximum of 4 pages for technical content including figures and possible references, and with one additional optional 5th page containing only references. Because our workshop papers will appear at IEEE Xplore, paper submissions and the reviewing process will be conducted through the ICASSP-2023 paper management system (Microsoft CMT) at https://cmt3.research.microsoft.com/ICASSP2023/Submission/Index.

When submitting, please indicate whether you prefer an oral/signed, presentation or a poster.
ATTENTION Please note that you are expected to submit the full paper, not an extended abstract as in previous years.