Audemy — AI Audio-Based Adaptive Learning Platform for Blind and Visually Impaired Students

Audemy is an AI audio-based learning platform built specifically for blind and visually impaired (BVI) K-12 students. It was developed by then-high-school student Crystal Yang, with AI-PC hardware and local on-device AI processing support from Intel.

The platform was co-designed over roughly a year through structured interviews with 20 educators specializing in accessibility, drawn from 8 schools that serve BVI students; researchers coded the interview transcripts into themes that directly shaped three adaptive features — question difficulty tuned to student accuracy, content pacing tuned to how often a student needs repetition, and delivery of material in multiple formats (direct questions versus real-world application framing).

A deliberate privacy design choice runs the AI functions locally on Intel-powered hardware rather than sending student audio to the cloud — notable given the sensitivity of routing a vulnerable population's voice data through third-party servers.

Audemy now reports over 2,000 BVI student users. However, the peer-reviewed paper describing its design presents no controlled outcome study: the only performance figure available (one student's 28% one-month math-score improvement) is a single anecdote, not a study result, and the paper's own authors note the system still cannot interpret complex emotional states, make context-sensitive decisions from audio cues, or provide tactile feedback.

Read the full analysis: https://pulse2.com/audemy-profile-crystal-yang-interview/