Electric Network Frequency Detection Using Least Absolute Deviations
Christos Korgialas, Constantine Kotropoulos
Abstract
Electric Network Frequency (ENF) is a fingerprint in multi-media forensics applications. ENF is a weak signal that is difficult to be detected. This difficulty stems from the existence of colored wide-sense stationary Gaussian noise in ENF as well as due to many unknown random parameters. However, several ENF detectors have been proposed, motivating the related research. In this paper, a novel Least Absolute Deviations-based ENF detector is proposed that is coined as LAD-Likelihood Ratio Test (LAD-LRT). The performance of the LAD-LRT detector is thoroughly analyzed concerning test statistic distribution and threshold selection. The aim is to develop a detector that detects ENF more accurately in short-length recordings than the state-of-the-art Least-Squares (LS)-LRT and naive-LRT detectors. Thorough evaluation using benchmark audio recordings demonstrate the effectiveness of the proposed detector.
BibTeX
@inproceedings{icassp2023_electricnetworkf,
title = {Electric Network Frequency Detection Using Least Absolute Deviations},
author = {Christos Korgialas and Constantine Kotropoulos},
booktitle = {ICASSP 2023},
year = {2023}
}