AiSL

Real-time speech-to-sign translation

Role
Lead product designer, cross-org team
Origin
Amazon org-wide hackathon (Concept)
Scope
0 → 1 product design

Deaf and hard-of-hearing employees in live meetings lacked access to the full context of the conversation, causing them to miss important information shared by speakers. Sign-language interpretation is limited to large-scale events due to staffing and setup costs — AiSL (AI Sign Language) was designed to make it available for every event, regardless of size.

"What other people don't realize is that though closed captions are helpful, they are not as good as ASL (American Sign Language). We are losing a lot of the emotional tone and nuances of the speaker."

— Viewer with hearing impairments
The proposal
An AI-powered real-time speech-to-sign language translation system that converts spoken audio into ASL using lifelike animated avatars, designed to operate within the timing constraints of natural conversation.
Recognized among 20+ competing projects
AiSL was recognized as Best UX and Best Accessible Use of AI at the hackathon — voted by judges across the organization.

Design highlights

Latency-first interaction model
Latency-first interaction model
Every design decision was tested against whether it preserved conversational flow, not just translation accuracy

Reflection: A hackathon timeline meant I optimized for proof-of-concept over edge cases — next iteration needs testing for capturing the tone and nuances of the speaker, background noise, and multi-speaker overlap.

All work TIBCO