Skip to content
← Creative

DuoSign

Text-to-Sign Language Translation

Built a full-stack accessibility app achieving 57% accuracy across 200+ ASL classes on the WLASL dataset

Role
Lead Developer / Researcher
Year
2025
Discipline
Research, Machine learning, Coding
For
Study
Tools
React, Python, MediaPipe, Three.js, NLP, Computer Vision, 3D Rendering, Inverse Kinematics, ASL, Accessibility

The process

  1. 01

    Problem statement

    Deaf and hearing people still lack quick, everyday translation between English and American Sign Language.

  2. 02

    Research & design thinking

    I split the problem in two: understanding the sentence (text-to-gloss) and performing it (avatar + inverse kinematics). Keeping the gloss layer explicit made the avatar debuggable, at the cost of some natural phrasing.

  3. 03

    Solution

    A React + Three.js signing avatar driven by a text-to-gloss NLP pipeline, plus live sign recognition with MediaPipe.

  4. 04

    Outcome

    57% average accuracy across 200+ ASL classes on WLASL.

Gallery

Commission something like thisNext: GlamPhotoBooth GH →