Date of Award
Master of Science
Mark E Dean
Garrett S Rose, Jon M Hathaway
Audio event detection and analysis is an important tool in many fields, from entertainment to security. Recognition technologies are used daily for parsing voice commands, tagging songs, and real time detection of crimes or other undesirable events. The system described in this work is a hardware based application of an audio detection system, implemented on an FPGA. It allows for the detection and characterization of gunshots and other events, such as breaking glass, by comparing a recorded audio sample to 20+ stored fingerprints in real time. Additionally, it has the ability to record flagged events and supports integration with mesh networks to send alerts.
Tobin, Jacob Daniel, "A Hardware Based Audio Event Detection System. " Master's Thesis, University of Tennessee, 2015.