Digital Audio Tampering Detection Based on ENF Consistency

This paper addresses a method of automatic detection of digital audio signal tampering based on feature fusion. Aiming at the insertion and deletion operations in the digital audio signal tamper chain. In this paper, the Electric Network Frequency (ENF) component of the digital audio signal is extracted and the consistency of the ENF component is analyzed to determine whether the audio signal is tampered with. In this paper, a general framework for passive tamper detection of audio signal based on ENF component consistency and a general framework for ENFC feature extraction are proposed. The feature set is used to quantify the amplitude of the phase and instantaneous frequency variations of the ENF component and to serve as an indicator of the consistency of the ENF component. SVM classifier is used to classify the extracted feature sets. The experimental results show that this method can classify the original signal and the edit signal which is inserted and deleted.