Making Technology More Accessible with .NET and AI
summary
Project Enabled Play proves a concrete accessibility pipeline: a .NET/Maui app plus Azure back end and SignalR, hardware HID emulation via Arduino Leonardo (later a custom board with Raspberry Pi compute module 4), and offline ML using Onnx models and offline ASR. It converts voice, face, gestures, phone tilt and Twitch chat into USB HID events, wins two accessibility hackathons, runs across a dozen platforms, achieves ~30 ms local command latency, and ships to schools.
AI-written summary · about
chapters (7)
- 0:00Accessible AI in .NET
- 3:18Accessibility challenges
- 11:17Prototype to assistive tech
- 18:54Scaling voice and facial input
- 24:32Performance and privacy for Enabled Play
- 30:11Demo: Enabled Play multi-input
- 33:47Pilot program and call to action
related talks
55mMaking Every Game and App More Accessible with .NET and AI
42mMaking Every Game More Accessible with .NET and AI
57mApplied AI and Accessibility to Play Games in New Ways
40mMicrosoft AI for Inclusion and Innovation
48mProgramming for Accessibility
47mAccessibility in the era of generative AI
23mDesigning for Accessibility
46mBuilding accessible experiences with AI