24 November 2022

Seventh internal SignON seminar

On the 7th of November we organised another internal seminar. Ruth Holmes (University College Dublin) took us through the UCD research on Signer Independent Sign Language Recognition. Sign language recognition comes with a number of significant challenges, including potential influences on real world recap and a lack of signer variety in the dataset. That is why the research was based on a specific dataset of ISL hand gestures signed by 6 individuals and with variety in input representation. Each hand gesture was described by 21 keypoints and trained on a variety of individuals. Different finetuning strategies led to different effects on generalisation in sign language recognition. Often there was bias and misclassification of signs. We remember that sign language recognition is still very much a work in progress and are glad to have some suggestions on how to move the research forward. Thanks, Ruth, for sharing this with us.

About SignON

SignON is a user-centric and community-driven project that aims to facilitate the exchange of information among Deaf, hard of hearing and hearing individuals across Europe, targeting the Irish, British, Dutch, Flemish and Spanish sign as well as the English, Irish, Dutch and Spanish spoken languages.
This project has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No. 101017255.
Designed and Developed by WP Ability