Microphone Array Based Surveillance Audio Classification

TL;DR

This study evaluates classical classifiers and beamforming algorithms for surveillance audio detection using microphone arrays, highlighting the trade-offs between accuracy and computational efficiency under various noise conditions.

Contribution

It compares multiple classifiers and beamforming techniques, identifying effective combinations and analyzing their performance and computational costs in surveillance audio classification.

Findings

SVM with Delay-and-Sum achieved 86% accuracy but with high computational cost.

SGD classifier provided comparable accuracy (~85%) with faster processing (~165 ms).

Performance varies with SNR levels and data augmentation improves results.

Abstract

The work assessed seven classical classifiers and two beamforming algorithms for detecting surveillance sound events. The tests included the use of AWGN with -10 dB to 30 dB SNR. Data Augmentation was also employed to improve algorithms' performance. The results showed that the combination of SVM and Delay-and-Sum (DaS) scored the best accuracy (up to 86.0\%), but had high computational cost ($\approx $ 402 ms), mainly due to DaS. The use of SGD also seems to be a good alternative since it has achieved good accuracy either (up to 85.3\%), but with quicker processing time ($\approx$ 165 ms).