Xiaojun Bi
Stony Brook University, NY·Computer Science
Typing and fixing text is roughly 40% of what people do on a smartphone, and for blind users it is a bottleneck. Measured typing speeds on touchscreen keyboards are about 4-5 words per minute for blind users against roughly 36 for sighted users.
- Fields
Computer Science
Engineering
- Topics
human-computer interaction
accessibility
blind users
- Grants
- 1 known grant, through Jan 2027
What they work on
- Create a non-visual free-form gesture input method that lets blind users enter whole words or phrases by tracing continuous gestures on the standard Qwerty touchscreen keyboard, removing the need to confirm each letter.
- Build an intelligent Braille soft keyboard with automatic error correction and auto-completion of unentered letters, and measure how much it reduces the error-prone touch input of blind users.
- Develop text-editing methods that combine language models with speech and touch so blind users can correct dictated text without relying on precise cursor movement.
- Evaluate the resulting input and editing methods with blind smartphone users, quantifying gains in text entry speed, error rate, and editing performance against current methods.
More about the research
Dictation helps, but studies show blind users spend about 80% of their time correcting what speech recognition produced, a slow and tiring process that depends on moving a cursor precisely to the right character. This project builds smarter input and editing methods so that blind smartphone users can write and revise text closer to the speed sighted users manage.
Why it matters
Essential services, from banking and shopping to staying in touch and travel, increasingly arrive through smartphones, and slow text entry limits how fully blind users can take part. Faster gesture typing, auto-correcting Braille keyboards, and voice-plus-touch editing could remove a daily productivity barrier for blind smartphone users and make these devices practical for work and participation in the digital economy.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Nicholas A Giudice
University of Maine, ME·Computer Science
Develop user-centered design guidelines that specify which information and sensory pairings, such as speech, sound or touch, best support the most common navigation tasks across a whole trip for blind and visually impaired travelers.
Hae-Na Lee
Michigan State University, MI·Computer Science
Develop detection algorithms that analyze webpage layouts, interaction workflows, user actions, and accessible navigation paths to identify deceptive design patterns, including ones created by mismatches between a page's visual structure and its screen reader reading order.
Jenna Gorlewicz
Saint Louis University, MO·Engineering
Build the core content platform for Inclusio, a system that takes graphics in many data formats and outputs them to web and mobile apps, braille and tactile embossers, multimodal touchpads, and refreshable tactile displays.
The school
Stony Brook University: 32 labs on PI Pages, $319M a year on research, 289 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.