Evaluating digital audio authenticity with spectral distances and ENF phase change

This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.