Search for: All records

To make it easier to add American Sign Language (ASL) to websites, which would increase information accessibility for many Deaf users, we investigate software to semi-automatically produce ASL animation from an easy-to-update script of the message, requiring us to automatically select the speed and timing for the animation. While we can model speed and timing of human signers from video recordings, prior work has suggested that users prefer animations to be slower than videos of humans signers. However, no prior study had systematically examined the multiple parameters of ASL timing, which include: sign duration, transition time, pausing frequency, pausing duration, and differential signing rate. In an experimental study, 16 native ASL signers provided subjective preference judgements during a side-by-side comparison of ASL animations in which each of these five parameters was varied. We empirically identified and report users' preferences for each of these individual timing parameters of ASL animation. 

Video-based eye trackers increasingly have potential to improve on-screen magnification for low-vision computer users. Yet, little is known about the viability of eye tracking hardware for gaze-guided magnification. We employed a magnification prototype to assess eye tracking quality for low-vision users as they performed reading and search tasks. We show that a high degree of tracking loss prevents current video-based eye tracking from capturing gaze input for low-vision users. Our findings show current technologies were not made with low vision users in mind, and we offer suggestions to improve gaze-tracking for diverse eye input. 

We evaluated whether DHH individuals benefit from the addition of subtle visual effects to captioned educational videos to guide their gaze toward potentially informative content.