Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition

TL;DR

This paper presents an embedded AI system utilizing natural language processing to detect violent and abusive speech silently, aiming to improve safety measures with a small, robust, and potentially commercializable solution.

Contribution

The study introduces a novel embedded AI approach for violence detection through speech analysis, combining NLP techniques with data augmentation for robustness.

Findings

Support vector machine achieved high accuracy with the proposed features.

Word embeddings and data augmentation improved model robustness.

Final model footprint is less than 10 MB, suitable for embedded devices.

Abstract

Violence is an epidemic in Brazil and a problem on the rise world-wide. Mobile devices provide communication technologies which can be used to monitor and alert about violent situations. However, current solutions, like panic buttons or safe words, might increase the loss of life in violent situations. We propose an embedded artificial intelligence solution, using natural language and speech processing technology, to silently alert someone who can help in this situation. The corpus used contains 400 positive phrases and 800 negative phrases, totaling 1,200 sentences which are classified using two well-known extraction methods for natural language processing tasks: bag-of-words and word embeddings and classified with a support vector machine. We describe the proof-of-concept product in development with promising results, indicating a path towards a commercial product. More importantly we show that model improvements via word embeddings and data augmentation techniques provide an intrinsically robust model. The final embedded solution also has a small footprint of less than 10 MB.