Audio forensics using acoustic environment traces

Abstract

Acoustic environment leaves its fingerprint in the audio recording captured in it. Acoustic reverberation and background noise are generally used to characterize an acoustic environment. Acoustic reverberation depends on the shape and the composition of a room, whereas, the background noise can be modeled using a dynamical random process. Inconsistencies in the acoustic environment traces can be used in a forensic and ballistic settings and acoustic environment identification (AEI). We describe a statistical framework to characterize recording environment. The proposed scheme uses inverse filtering to estimate reverberation component and particle filtering to estimate background noise from audio recording. A multi-class support vector machine (SVM) classifier is used for AEI. Experimental results show that the proposed system can successfully identify a recording environment for regular as well as blind AEI.