Combining ENF phase discontinuity checking and temporal pattern matching for audio tampering detection

Abstract

In this paper, we present an improved approach for audio tampering detection and localization based on the Electrical Network Frequency (ENF) analysis, combining analysis of the ENF phase, and ENF temporal pattern matching: The proposed algorithm uses phase discontinuity checking to detect regions that might have been tampered, which are then matched against an ENF reference database to validate order and duration of the detected regions. Using this approach, the false-positive rate can be reduced from ≈ approx 55% using phase analysis to ≈ approx 10% using the combined approach, thus improving overall reliability of the tampering detection approach.