Real-Time Emergency Vehicle Detection using Mel Spectrograms and Regular Expressions

TL;DR

This paper introduces a real-time emergency vehicle siren detection method using Mel spectrograms and regular expressions, comparing DSP techniques with deep neural networks for accuracy, efficiency, and practicality.

Contribution

It presents a novel, low-cost, and energy-efficient DSP-based approach for real-time siren detection, outperforming neural networks in portability and interpretability.

Findings

DSP algorithm has slightly lower accuracy than DNN.

DSP method is more portable and energy-efficient.

Both methods effectively classify siren sounds.

Abstract

In emergency situations, the high-speed movement of an ambulance through the city streets can be hindered by vehicular traffic. This work presents a method for detecting emergency vehicle sirens in real time. To obtain the audio fingerprint of a Hi-Lo siren, DSP and signal symbolization techniques were applied, which were contrasted against an audio classifier based on a deep neural network, using the same 280 audios of ambient sounds and 52 Hi-Lo siren audios dataset. In both methods, some classification accuracy metrics were evaluated based on its confusion matrix, resulting in the DSP algorithm having a slightly lower accuracy than the DNN model, however, it offers a self-explanatory, adjustable, portable, high performance and lower energy and consumption that makes it a more viable lower cost ADAS implementation to identify Hi-Lo sirens in real time.