FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones

TL;DR

FSboard is the largest ASL fingerspelling dataset to date, collected via smartphones, enabling progress in sign language recognition with practical, real-world data and demonstrating baseline recognition performance.

Contribution

The paper introduces FSboard, a large-scale, smartphone-collected ASL fingerspelling dataset, and provides initial recognition benchmarks demonstrating its utility.

Findings

Largest dataset with over 3 million characters

Baseline recognition achieves 11.1% CER with simple models

Model performance degrades gracefully with reduced frame rate

Abstract

Progress in machine understanding of sign languages has been slow and hampered by limited data. In this paper, we present FSboard, an American Sign Language fingerspelling dataset situated in a mobile text entry use case, collected from 147 paid and consenting Deaf signers using Pixel 4A selfie cameras in a variety of environments. Fingerspelling recognition is an incomplete solution that is only one small part of sign language translation, but it could provide some immediate benefit to Deaf/Hard of Hearing signers as more broadly capable technology develops. At >3 million characters in length and >250 hours in duration, FSboard is the largest fingerspelling recognition dataset to date by a factor of >10x. As a simple baseline, we finetune 30 Hz MediaPipe Holistic landmark inputs into ByT5-Small and achieve 11.1% Character Error Rate (CER) on a test set with unique phrases and signers. This quality degrades gracefully when decreasing frame rate and excluding face/body landmarks: plausible optimizations to help models run on device in real time.