Kavach
AI-powered voice authentication and physical smart access system.
01 · The Problem & Hypothesis
Why this needed to be built
People frequently forget physical keys, while traditional contact biometrics require physical touch and specialized optical sensors. We asked: What if human voice could securely become the key?
Turn human voice into a biometric key by integrating real-time deep learning speaker verification with a Raspberry Pi server, Arduino microcontroller, and electromechanical motor actuators.
02 · Technical Implementation
How the system was architected
Built as a 5-person engineering team at NIT Jalandhar. Kavach was my first production-grade project integrating hardware, software, voice biometrics, and databases. During testing, we uncovered a critical vulnerability: if an unauthorized person spoke the exact trigger keyword, the system could unlock. We diagnosed the acoustic flaw and re-engineered a two-tier pipeline cross-referencing biometric voiceprint spectrograms with phrase matching before sending serial signals to the Arduino.
03 · Key Takeaways Earned
“Building something real is fundamentally different from writing code that runs in a notebook.”
“Hardware and acoustic edge cases require defensive engineering and isolated power topologies.”
“End-to-end building means taking total ownership from the audio capture to the mechanical actuator.”