A Mobile Application for the Immediate Detection and Response to Violent Attacks in Urban Environments Utilizing Speech-to-Text and Natural Language Processing

Doig A.; Abanto N.; Wong L. · Engineering, Technology and Applied Science Research (2025) · DOI: 10.48084/etasr.13189

Resumen

The increase in violent attacks in urban environments has generated growing social concern about improving emergency response speed, considering that a large portion of the population has experienced some form of violence in public spaces. This study aims to build a mobile application for the immediate detection and response to violent situations using advanced technologies such as Speech-to-Text (STT) and Natural Language Processing (NLP). The development was carried out in four phases: (1) selection of STT service, (2) selection of NLP service, (3) Implementation of STT and NLP, and (4) application development. Additionally, an experiment was conducted in two simulated scenarios representing armed assaults, evaluating reaction times, Help Request Time (HRT), and total response time, both with and without the use of the application. The results showed a significant reduction in total response time, 50.35% in the first scenario and 43.92% in the second. Moreover, the application was evaluated by users and security experts, obtaining highly favorable scores in effectiveness, efficiency, and overall satisfaction. It is concluded that this technological solution represents an effective and practical tool for substantially improving speed and safety in critical situations, enabling more timely and efficient intervention. © (2025), (Dr D. Pylarinos). All right reserved.

Instituciones: Universidad Peruana de Ciencias Aplicadas