Audio Recording Location Identification Using Acoustic Environment Signature

• Published in: IEEE transactions on information forensics and security Vol. 8; no. 11; pp. 1746 - 1759
• Main Authors: Hong Zhao, Malik, Hafiz
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustic environment identification; Acoustic noise; acoustic reverberation; Acoustical measurements and instrumentation; Acoustics; audio forensics; Audition; Background noise; Biological and medical sciences; Digital music; Estimates; Exact sciences and technology; Filtering; Fundamental and applied biological sciences. Psychology; Fundamental areas of phenomenology (including applications); Microphones; Noise measurement; particle filtering; Particle filters; Perception; Physics; Psychology. Psychoanalysis. Psychiatry; Psychology. Psychophysiology; Recording; Reverberation; Spectra; Studies; Temporal logic; Transduction; acoustical devices for the generation and reproduction of sound; Psychoacoustics; Sound recording; audio forensics; Data compression; Non linear filter; Secondary source; Background noise; Line broadening; particle filtering; Audio acoustics; Ballistics; Robustness; System identification; Localization; Particle filter; Content analysis; Sound record; Acoustic reverberation; Monte Carlo method; Statistical analysis; Acoustic measurement; Forensic science; Experimental study; Spectral analysis; Non linear filtering; Acoustic environment identification; Particle method; Experimental result; Cepstrum; Pitch(acoustics); Signal distortion
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2013.2278843

An audio recording is subject to a number of possible distortions and artifacts. Consider, for example, artifacts due to acoustic reverberation and background noise. The acoustic reverberation depends on the shape and the composition of the room, and it causes temporal and spectral smearing of the recorded sound. The background noise, on the other hand, depends on the secondary audio source activities present in the evidentiary recording. Extraction of acoustic cues from an audio recording is an important but challenging task. Temporal changes in the estimated reverberation and background noise can be used for dynamic acoustic environment identification (AEI), audio forensics, and ballistic settings. We describe a statistical technique based on spectral subtraction to estimate the amount of reverberation and nonlinear filtering based on particle filtering to estimate the background noise. The effectiveness of the proposed method is tested using a data set consisting of speech recordings of two human speakers (one male and one female) made in eight acoustic environments using four commercial grade microphones. Performance of the proposed method is evaluated for various experimental settings such as microphone independent, semi- and full-blind AEI, and robustness to MP3 compression. Performance of the proposed framework is also evaluated using Temporal Derivative-based Spectrum and Mel-Cepstrum (TDSM)-based features. Experimental results show that the proposed method improves AEI performance compared with the direct method (i.e., feature vector is extracted from the audio recording directly). In addition, experimental results also show that the proposed scheme is robust to MP3 compression attack.