GUNSHOT DETECTION

This project focuses on developing a gunshot detection system capable of distinguishing gunshot sounds from non-gunshot sounds. A Recurrent Neural Network (RNN) model is trained using audio datasets and achieves high accuracy for prerecorded audio. The system is further tested on live audio, where challenges in maintaining accuracy are observed. Feature extraction techniques, such as MFCC, are employed to enhance the detection process. The results demonstrate the system’s potential for real-time applications with scope for improving live detection accuracy.