Sanket
Assistive app for the deaf and hard of hearing with ML-powered environmental sound detection.
- Assistive Tech
- Audio ML
- Speech Recognition
Overview
Sanket is an assistive application for people who are deaf or hard of hearing, with backend and machine learning components built by Ashish Pandey. It detects wake words, recognizes speakers, and identifies critical environmental sounds such as fire alarms, sirens, and baby cries, delivering vibration alerts in real time.
What Ashish Pandey built
- Developed backend and ML components focused on accessibility for the deaf and hard of hearing
- Implemented vibration alerts for wake word detection (93% accuracy) and speaker recognition (94%)
- Enabled detection of critical sounds fire alarms, sirens, baby cries at 89% accuracy
Tech stack
- Python
- PyTorch
- TensorFlow
- FastAPI
More projects by Ashish Pandey
- MemBlocks Modular memory management system for LLMs with isolated, shareable context spaces per conversation.
- TimelyMeet AI-powered meeting management app with multi-agent scheduling and email automation.
- Desktop AI Assistant Voice-controlled system automation agent enabling hands-free control, email, and browser automation.