AMR Compressed-Domain Analysis for Multimedia Forensics Double Compression Detection
Main Article Content
Abstract
An audio recording must be authentic to be admitted as evidence in a criminal prosecution so that the speech is saved with maximum fidelity and interpretation mistakes are prevented. AMR (adaptive multi-rate) encoder is a worldwide standard for speech compression and for GSM mobile network transmission, including 3G and 4G. In addition, such encoder is an audio file format standard with extension AMR which uses the same compression algorithm. Due to its extensive usage in mobile networks and high availability in modern smartphones, AMR format has been found in audio authenticity cases for forgery searching. Such exams compound the multimedia forensics field which consists of, among other techniques, double compression detection, i. e., to determine if a given AMR file was decompressed and compressed again. AMR double compression detection is a complex engineering problem whose solution is still underway. In general terms, if an AMR file is double compressed, it is not an original one and it was likely doctored. The published works in literature about double compression detection are based on decoded waveform AMR files to extract features. In this paper, a new approach is proposed to AMR double compression detection which, in spite of processing decoded audio, uses its encoded version to extract compressed-domain linear prediction (LP) coefficient-based features. By means of feature statistical analysis, it is possible to show that they can be used to achieve AMR double compression detection in an effective way, so that they can be considered a promising path to solve AMR double compression problem by artificial neural networks.
Article Details
The journal has exclusive rights over the first publication, printed and/or digital, of this academic text, which does not affect the copyright of the person responsible for the research.
The reproduction (in whole or in part) of the published material depends on the express mention of this journal as the origin, by citing the volume, edition number and the DOI link for cross-reference. For rights purposes, the original publication source must be recorded.
The use of the results published here in other vehicles of scientific divulgation, even if by the authors, depends on the express indication of this journal as a means of original publication, under penalty of characterizing a situation of self-plagiarism.
____________________________________________
Additional information and author statements
(scientific integrity)
Declaration of conflict of interest: The author(s) confirm that there are no conflicts of interest in conducting this research and writing this article.
Authorship statement: All and only researchers who meet the authorship requirements for this article are listed as authors; all co-authors are fully responsible for this work in its entirety.
Declaration of originality: The author(s) guarantee that the text published here has not been previously published elsewhere and that future republication will only be made with express reference to the original place of publication; also certifies that there is no plagiarism of third-party material or self-plagiarism.
____________________________________________
Archiving and distribution
The final published PDF can be archived, without restrictions, on any open access server, indexer, repository or personal page, such as Academia.edu and ResearchGate.
How to Cite
References
rd Generation Partnership Project (3GPP). AMR codec - Release 10, 2011. Available at: <http://www.3gpp.org/ftp/Specs/archive/26_series/26.104/>. Acessed: jan. 22 2018.
BATTIATO, S.; GIUDICE, O.; PARATORE, A. Multimedia Forensics: Discovering the History of Multimedia Contents. In: Proceedings of the 17th International Conference on Computer Systems and Technologies (CompSysTech), Palermo, Italy, p. 5-16, 2016.
ESQUEF, P. A. A.; APOLINÁRIO, Jr. A.; BISCAINHO, L. W. P. Edit Detection in Speech Recordings Via Instantaneous Electric Network Frequency Variations. IEEE Transactions on Information Forensics and Security, vol. 9, no. 12, p. 2314-2326, dec. 2014.
FARID, H. Detecting Digital Forgeries Using Bispectral Analysis. AI Lab, MIT Tech. Rep. AIM-1657, Boston, USA, 1999. Available at: <ftp://publications.ai.mit.edu/ai-publications/pdf/AIM-1657.pdf>. Acessed: jan. 22 2018.
GAROFOLO, J. S.; LAMEL, L. F.; FISHER, W. M.; FISCUS, J. G.; PALLETT, D.S.; DAHLGREN, L.; ZUE, V. TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1. Philadelphia: Linguistic Data Consortium, 1993. Avaliable AT: http:// https://catalog.ldc.upenn.edu/LDC93S1. Acessed: jan. 22 2018.
GRIGORAS, C. Forensic Analysis of the Digital Audio Recordings - The Electric Network Frequency Criterion, Forensic Science International, vol. 136, Suppl. 1, p. 368-369, 2003.
GUPTA, S.; CHO, S.; KUO, C. C. Current Developments and Future Trends in Audio Authentication. IEEE Multimedia, vol. 19, no. 01, p. 50-59, jan. 2012.
HANILÇI, C.; KINNUNNEN, T. Source Cell-Phone Recognition from Recorded Speech using Non-Speech Segments. Digital Signal Processing, no. 35, p. 75-85, 2014.
HIÇSÖNMEZ, S.; SENCAR, H. T.; AVCIBAS, I. Audio Codec Identification through Payload Sampling. In: Proc. Int. Workshop Inf. Forensics Secur., Iguacu Falls, Brazil, p. 1-6, 2011.
HIÇSÖNMEZ, S.; UZUN, E.; SENCAR, H. T.; Methods for Identifying Traces of Compression in Audio. In: Proc. 1st Int. Conf. Commun., Signal Process., Appl., Sharjah, United Arab Emirates, p. 1-6, 2013.
IKRAM, S.; MALIK, H. Digital Audio Forensics Using Background Noise. In: 2010 IEEE International Conference on Multimedia & Expo (ICME’2010), Singapore, p. 106-110, 2010.
JENNER, F.; KWASINSKI, A. Highly Accurate Non-Intrusive Speech Forensics for Codec Identifications from Observed Decoded Signals. In: Proc. 2012 IEEE International Conference on Acoustic, Speech and Signal Processing., Kyoto, Japan, p. 1737-1740, 2012.
KAJSTURA, M.; TRAWINSKA, A.; HEBENSTREIT, J. Application of the Electrical Network Frequency (ENF) Criterion: a Case of a Digital Recording. Forensic Science International, nº 155, p. 165-171, feb. 2005.
KORYCKI, R. Detection of Montage in Lossy Compressed Digital Audio Recordings. Archives of Acoustics, vol. 39, no. 1, p. 67-52, feb. 2014.
LIU, Q.; SUNG, A. H.; QIAO, M. Detection of Double MP3 Compression. Cognitive Computation., vol.2, no. 4, p. 291-296, 2010.
LUO, D.; LUO, W.; YANG, R.; HUANG, J. Compression History Identification for Digital Audio Signal. In: Proc. 2012 IEEE International Conference on Acoustic, Speech and Signal Processing., Kyoto, Japan, p. 1732-1736, 2012.
LUO, D.; LUO, W.; YANG, R.; HUANG, J. Identifying Compression History of Wave Audio and its Applications. ACM Trans. Multimedia Comput., Commun., Appl., vol. 10, no. 3, p. 30-1 - 30-19, 2014.
LUO, D.; YANG, R.; HUANG, J. Detecting Double Compressed AMR Audio using Deep Learning. In: 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP’2014), Florence, Italy, p. 2688-2692, 2014.
LUO, D.; YANG, R.; LIN, B.; HUANG, J. Detection of Double Compressed AMR Audio Using Stacked Autoencoder. IEEE Transactions on Information Forensics and Security, vol. 12, no.2, p. 432-444, 2017.
MALIK, H. Acoustic Environment Identification and Its Applications to Audio Forensics. IEEE Transactions on Information Forensics and Security, vol. 8, no. 11, p. 1827-1837, nov. 2013.
PETRACCA, H.; SERVETTI, A.; DE MARTIN, J. C. Low-Complexity Automatic Speaker Recognition in the Compressed GSM AMR Domain In: Proc. IEEE Int. Conf. Multimedia and Expo (ICME), Amsterdam, Netherlands, 2005.
PFEIFFER, S.; VINCENT, T. Survey of Compressed Domain Audio Features and their Expressiveness. In: Proc. SPIE Conf. Electronic Imaging, San Francisco, USA, p. 133-147, 2003.
QIAO, M.; SUNG, A. H.; LIU, Q. Revealing Real Quality of Double Compressed MP3 Audio. In: Proc. Int. Conf. Multimedia, Florence, Italy, p. 1011-1014, 2010.
REIS, P. M. G. I.; COSTA, J. P. C. L.; MIRANDA, R. K.; DEL GALDO, G. ESPRIT-Hilbert-based Audio Tampering Detection with SVM Classifier for Forensic Analysis Via Electrical Network Frequency. IEEE Transactions on Information Forensics and Security, vol. 12, no. 4, p. 853-864, apr. 2017.
RODRÍGUEZ, D. P. N.; APOLINÁRIO, J. A.; BISCAINHO, L. W. P. Audio Authenticity: Detecting ENF Discontinuity with High Precision Phase Analysis. IEEE Transactions on Information Forensics and Security, vol. 5, no. 3, p. 534-543, sep. 2010.
ROMERO, D.; WILSON, C. Y. Automatic Acquisition Device Identification from Speech Recordings. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’2010), 2010, Texas, USA, p. 1806-1809, 2010.
SHEN, Y.; JIA, J.; CAI, L. Detecting Double Compressed AMR-format Audio Recordings. In: Proc. 10th Phonetics Conf. China (PCC), China, p. 1-5, 2012.
SU, H.; GARG, R.; HAJJ-AHMAD, A.; WU, M. ENF Analysis on Recaptured Audio Recordings. In: 2013 IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), Canada, p. 3018-3022, 2013.
YANG, R.; QU, Z.; HUANG, J. Exposing MP3 Audio Forgeries Using Frame Offsets. ACM Transactions on Multimedia Computing, Communications and Applications, vol. 8, no. S2, p. 35:1-35:20, sep. 2012.
YANG, R.; SHI, Y. Q.; HUANG, J. Defeating Fake-quality MP3. In: Proc. ACM Workshop Multimedia Security, New Jersey, USA, p. 117-124, 2009.
YANG, R.; SHI, Y. T.; HUANG, J. Detecting Double Compression of Audio Signal. In: Proc. SPIE Conference on Media Forensics and Security II, San Jose, USA, vol. 7541, p. 1-10, 2010.
ZAKARIAH, M.; KHAN, M. K.; MALIK, H. Digital Multimedia Audio Forensics: Past, Present and Future. Multimedia Tools and Applications, vol. 77, p. 1009-1040, 2017.