Human Scream Detection and Analysis to Control Crime Rate using Machine Learning

Abstract

Public safety is significantly hampered by delayed police response due to a lack of accurate and timely information about crimes. Human scream detection using audio classification offers a promising solution. This work presents a novel three- phase scream detection system leveraging a K-Nearest Neighbors (KNN) classifier and a Multilayer Perceptron (MLP) model. The system first separates human distress sounds from back- ground noise using MFCC features and KNN. Subsequently, it differentiates screams from shouts within the distress category using another KNN classifier. Finally, the classified screams trigger emergency notifications sent to the police station via the Twilio library. Our proposed system offers a robust and layered approach to scream detection, potentially enhancing response times and improving public safety. Index Terms—MFCCs, KNN, Multilayer perceptron model, Scream Detection.