ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition
This work addresses communication inequities for D/deaf people by improving sign language dictionary retrieval, though it is incremental as it builds on existing ISLR methods with a new dataset.
The authors tackled the problem of isolated sign language recognition by releasing ASL Citizen, a crowdsourced dataset with 83,399 videos for 2,731 signs, and showed that training classifiers on it advances state-of-the-art for dictionary retrieval, achieving 63% accuracy and 91% recall-at-10 on unseen users.
Sign languages are used as a primary language by approximately 70 million D/deaf people world-wide. However, most communication technologies operate in spoken and written languages, creating inequities in access. To help tackle this problem, we release ASL Citizen, the first crowdsourced Isolated Sign Language Recognition (ISLR) dataset, collected with consent and containing 83,399 videos for 2,731 distinct signs filmed by 52 signers in a variety of environments. We propose that this dataset be used for sign language dictionary retrieval for American Sign Language (ASL), where a user demonstrates a sign to their webcam to retrieve matching signs from a dictionary. We show that training supervised machine learning classifiers with our dataset advances the state-of-the-art on metrics relevant for dictionary retrieval, achieving 63% accuracy and a recall-at-10 of 91%, evaluated entirely on videos of users who are not present in the training or validation sets. An accessible PDF of this article is available at the following link: https://aashakadesai.github.io/research/ASLCitizen_arxiv_updated.pdf