Robust Speech Hashing for Digital Audio Forensics
Source abstract
Abstract
The verification of the integrity and authenticity of multimedia content is an essential task in the forensic field, in order to make digital evidence admissible. The main objective is to establish whether the multimedia content has been manipulated with significant changes to its content, such as the removal of noise (e.g., a gunshot) that could clarify the facts of a crime. In this project we propose a method to generate a summary value for audio recordings, known as hash. Our method is robust, which means that if the audio has been modified slightly (without changing its significant content) with perceptual manipulations such as MPEG-4 AAC, the hash value of the new audio is very similar to that of the original audio; on the contrary, if the audio is altered and its content changes, for example with a low pass filter, the new hash value moves away from the original value. The method starts with the application of MFCC (Mel-frequency cepstrum coefficients) and the reduction of dimensions through the analysis of main components (principal component analysis, PCA). The reduced data is encrypted using as inputs two values from a particular binarization system using Collatz conjecture as the basis. Finally, a robust 96-bit code is obtained, which varies little when perceptual modifications are made to the signal such as compression or amplitude modification. According to experimental tests, the BER (bit error rate) between the hash value of the original audio recording and the manipulated audio recording is low for perceptual manipulations, i.e., 0% for FLAC and re-quantization, 1% in average for volume (−6 dB gain), less than 5% in average for MPEG-4 and resampling (using the FIR anti-aliasing filter); but more than 25% for non-perceptual manipulations such as low pass filtering (3 kHz, fifth order), additive noise, cutting and copy-move.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital Media Forensic Detection · Music and Audio Processing · Video Analysis and Summarization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering, Universidad Militar Nueva Granada, Bogotá 110111, Colombia
Funding
Universidad Militar Nueva Granada
References (40)
Show source-provided references
1. Authenticity verification of audio signals based on fragile watermarking for audio forensics10.1016/j.eswa.2017.09.003 ↗
2. A high-performance speech perceptual hashing authentication algorithm based on discrete wavelet transform and measurement matrix10.1007/s11042-018-5613-5 ↗
3. Audio Watermarking Based on Fibonacci Numbers10.1109/TASLP.2015.2430818 ↗
4. Text Hiding in Images Based on QIM and OVSF10.1109/TLA.2016.7459600 ↗
5. Gonzalez, F.P., Alfaro, P.C., Freire, L.P., and Vieites, D.P. (2016). Method and System for Robust Audio Hashing. (9,286,909), U.S. Patent.
6. Computer forensics: The need for standardization and certification
7. Digital forensics [From the Guest Editors]10.1109/MSP.2008.931089 ↗
8. Choo, M.J., and Huh, J.H. (2019). Digital Forensics System Using PLC for Inter-Floor Noise Measurement: Detailing PLC-Based Android Solution Replacing CCTV-based Solution. Electronics, 8.10.3390/electronics8101091 ↗
9. Audio forensic examination10.1109/MSP.2008.931080 ↗
10. Maher, R.C. (2010). Overview of Audio Forensics. Studies in Computational Intelligence, Springer.10.1007/978-3-642-11756-5_6 ↗
11. Acoustic Environment Identification and Its Applications to Audio Forensics10.1109/TIFS.2013.2280888 ↗
12. Digital multimedia audio forensics: Past, present and future10.1007/s11042-016-4277-2 ↗
13. Ho, A.T.S., and Li, S. (2015). Handbook of Digital Forensics of Multimedia Data and Devices, Wiley-IEEE Press. [1st ed.].10.1002/9781118705773 ↗
14. Renza, D., Arango, J., and Ballesteros, D. (2019). A mobile-oriented system for integrity preserving in audio forensics. Appl. Sci., 9.10.3390/app9153097 ↗
15. SWGIT (2012). Best Practices for Maintaining the Integrity of Digital Images and Digital Video, SWGIT Document Section 13, Scientific Working Group on Imaging Technology. Version 1.1; Technical Report.
16. Perceptual Audio Hashing Functions10.1155/ASP.2005.1780 ↗
17. Yiqing Lin, W.H.A. (2014). Audio Watermark, Springer.
18. Wang, A.L.C., Wong, C., and Symons, J. (2011). Method and System for Identification of Distributed Broadcast Content. (8,086,171), U.S. Patent.
19. Wang, A.L.c., and Culbert, D. (2009). Robust and Invariant Audio Pattern Matching. (7,627,477), U.S. Patent.
20. Baluja, S., and Covell, M. (2010). Approximate Hashing Functions for Finding Similar Content. (7,831,531), U.S. Patent.
21. Robust audio hashing based on discrete-wavelet-transform and non-negative matrix factorization10.1049/iet-com.2009.0749 ↗
22. Nouri, M., Zeinolabedini, Z., Farhangian, N., and Fekri, N. (2012, January 17–19). Analysis of a novel audio hash function based upon stationary wavelet transform. Proceedings of the 2012 6th International Conference on Application of Information and Communication Technologies (AICT), Tbilisi, GA, USA.10.1109/ICAICT.2012.6398472 ↗
23. Zhang, Q., Qiao, S., Zhang, T., and Huang, Y. (2017, January 29–31). A fast speech feature extraction method based on perceptual hashing. Proceedings of the 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guilin, China.10.1109/FSKD.2017.8392951 ↗
24. Li, J., and Wu, T. (2015, January 19–20). Perceptual Audio Hashing Using RT and DCT in Wavelet Domain. Proceedings of the 2015 11th International Conference on Computational Intelligence and Security (CIS), Shenzhen, China.10.1109/CIS.2015.94 ↗
25. Audio hash function based on non-negative matrix factorization of Mel-frequency cepstral coefficients10.1049/iet-ifs.2010.0097 ↗
26. Maximum excursion and stopping time record-holders for the problem: Computational results10.1090/S0025-5718-99-01031-5 ↗
27. On the Collatz 3n + 1 Algorithm
28. About the Collatz conjecture10.1007/s002360050117 ↗
29. Han, W., Chan, C.F., Choy, C.S., and Pun, K.P. (2006, January 21–24). An efficient MFCC extraction method in speech recognition. Proceedings of the 2006 IEEE International Symposium on Circuits and Systems, Island of Kos, Greece.
30. INTERPOL survey of the use of speaker identification by law enforcement agencies10.1016/j.forsciint.2016.03.044 ↗
31. Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification10.1109/TASL.2012.2191960 ↗
32. Classification of speech dysfluencies with MFCC and LPCC features10.1016/j.eswa.2011.07.065 ↗
33. Rivest, R.L., Shamir, A., and Adleman, L.M. (1983). Cryptographic Communications System and Method. (4,405,829), U.S. Patent.
34. Speaker Recognition by Machines and Humans: A tutorial review10.1109/MSP.2015.2462851 ↗
35. Dhillon, I.S., and Sra, S. (2005, January 5–8). Generalized Nonnegative Matrix Approximations with Bregman Divergences. Proceedings of the Neural Information Processing Systems (NIPS), Vancouver, BC, Canada.
36. Jolliffe, I. (2002). Principal component analysis for time series and other non-independent data. Principal Component Analysis, Springer.
37. Haitsma, J., Kalker, T., and Oostveen, J. (2011, January 13–15). Robust audio hashing for content identification. Proceedings of the International Workshop on Content-Based Multimedia Indexing, Madrid, Spain.
38. Mıhçak, M.K., and Venkatesan, R. (2001). A Perceptual Audio Hashing Algorithm: A Tool for Robust Audio Identification and Information Hiding. Information Hiding, Springer.10.1007/3-540-45496-9_5 ↗
39. Audio Perceptual Hashing Based on NMF and MDCT Coefficients10.1049/cje.2015.07.024 ↗
40. An efficient speech perceptual hashing authentication algorithm based on wavelet packet decomposition