Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
Cybernetics And Systems Analysis
International Theoretical Science Journal
Volume 56 >>> № 2 MARCH — APRIL 2020
UDC 621.317+681.849
V.I. Solovyov1, O.V. Rybalskiy2, V.V. Zhuravel3


1 Volodymyr Dahl East Ukrainian National University, Sievierodonetsk, Ukraine

 edemsvi@gmail.com

2 National Academy of Internal Affairs, Kyiv, Ukraine

 rov_1946@ukr.net

3 Kyiv Expert and Forensic Center of the Ministry of Internal Affairs
of Ukraine, Kyiv, Ukraine

 fonoscopia@ukr.net

SUBSTANTIATING THE FUNDAMENTAL FITNESS OF DEEP LEARNNG
NEURON NETWORKS FOR CONSTRUCTION OF A SYSTEM
FOR DETECTING TRACES OF DIGITAL TREATMENT OF PHONOGRAMS

Abstract. On the model of a deep learning neuron network, the authors substantiate and verify ptincipal applicability of such network to create a highly efficient expert tool intended to detect traces of digital treatment in phonograms. An experiment is conducted on a large volume (more than 100,000) of experimental fragments of untilled pauses of phonograms and pauses with traces of treatment, obtained in the automatic mode. The obtained dependences showed that for the probability threshold over 0.55 correct binary classification of pauses there is a possibility of constructing a highly efficient tool of examination.

Keywords: deep learning neuron network, points of editing, digital treatment of a phonogram, digital phonogram, digital editing, examination.



FULL TEXT

REFERENCES

  1. ENFSI working group for forensic speech and audio analysis. URL: hppt://www.еnfsi.eu/ about-enfsi/structure/working-groups/speech-and-аudio.

  2. Korycki R. Methods of time-frequency analysis in authentication of digital audio recordings. INTL Journal of Electronics and Telecommunications. 2010. Vol. 56, N 3. P. 257–261.

  3. Nicolalde D.P., Apolinario J.A. Evaluating digital audio authenticity with spectral distances and ENF phase change. Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009. P. 1417–1420.

  4. Nicolalde D.P., Apolinario J.A., Biscainho L.W.P. Audio authenticity: Detecting ENF discontinuity with high precision phase analysis. IEEE Transactions on Information Forensics and Security. 2010. Vol. 5, Iss. 3. P. 534–543.

  5. Rappaport D. Establishing a standard for digital audio authenticity: A critical analysis of tools, methodologies, and challenges thesis directed by catalin grigoras. URL: http://aquarius.ime.eb.br /~apolin/papers/IEEETIFS2010Daniel.pdf.

  6. Cooper A.J. An automated approach to the Electric Network Frequency (ENF) criterion — Theory and practice. International Journal of Speech Language and the Law. 2009. Vol. 16, N 2. P. 193–218.

  7. Huijbregtse M., Geradts Z. Using the ENF criterion for determining the time of recording of short digital audio recordings. In: Computational Forensics. IWCF 2009. Lecture Notes in Computer Science. Geradts Z.J.M.H., Franke K.Y., Veenman C.J. (Eds). 2009. Vol 5718. P. 116–124.

  8. Catalin G. Statistical tools for multimedia forensics. The 39th AES International Conference Audio Forensics: Practices and Challenges (June 17, 2010), Hillerod, Denmark, 2010.

  9. Jenkins C.W. An investigative approach to configuring forensic electric network frequency databases. Master’s Thesis, University of Colorado Denver, 2011.

  10. Brixen E. Audio metering measurements, Standards and practices. Second ed. Oxford, United Kingdom: Focal Press, 2011. 264 p.

  11. Cooper A.J. Detection of copies of digital audio recordings produced using analogue interfacing. International Journal of Speech, Language, and the Law. 2008. Vol. 15, N 1. Р. 67–95.

  12. Grigoras C., Smith J.M., Jenkins C.W. Advances in ENF database configuration for forensic authentication of digital media. 131st Convention of the Audio Engineering Society (October 20–23, 2011), New York, 2011.

  13. Moon C.-B., Kim H., Kim B.M. Audio recorder identification using reduced noise features. In: Ubiquitous Information Technologies and Applications. Lecture Notes in Electrical Engineering. Berlin; Heidelberg: Springer, 2014. Vol. 280. P. 35–42.

  14. Aggarwal R., Singh S., Roul A.K., Khanna N. Cellphone identification using noise estimates from recorded audio. In: Communications and Signal Proc. (ICCSP), 2014 International Conference on. IEEE. 2014, P. 1218–1222.

  15. Rybalsky O.V. The use of wavelet analysis to detect traces of digital processing of analog and digital phonograms in forensic acoustic expertise [in Ukrainian]. Kyiv: Nats. akad. vnutr. sprav Ukrayiny, 2004. 167 p.

  16. Zhuravel V.V. Features of the formation of phonograms recorded from telephone channels. Suchasna spetsialʹna tekhnika.. 2015. N 4 (43). P. 26–31.

  17. Rybalsky O.V. Models of non-standard fake digital phonograms. Registration, Storage and Processing of Data. 2003. Vol. 5, N 4. P. 25–32.

  18. Bobritsky S.M., Storozhenko S.V. Investigation of the mounting of records made by digital recorders. Coll. of sciences. works "Theory and Practice of Forensics and Examination" [in Ukrainian]. Kharkiv: Pravo, 2011. Iss. 11. P. 353–361.

  19. Rybalsky O.V., Zharikov Yu.F. Modern methods for verifying the authenticity of magnetic phonograms in forensic acoustic examination. Kiev: Nats. akad. vnutr. del Ukrainy, 2003. 302 p.

  20. Rybalsky O.V. The main provisions of the theory of identifying traces of digital processing of phonograms and the features of its software and methodological implementation in the examination of materials and means of video audio recording. Part 1. Zahyst Informatcii. 2006. Vol. 8, N 1 (28). P. 71–76.

  21. Rybalsky O.V., Soloviev V.I., Zhuravel V.V. Traces of editing in digital phonograms made by the method of cutting and rearranging fragments. Registration, Storage and Processing of Data. 2016. Vol. 18, N 1. P. 32–41.

  22. Rybalsky O.V., Zhuravel V.V. Experimental confirmation of the simulation results of the mechanism of occurrence of identification signs of installation in digital phonograms. Modern Information and Electronic Technologies: Proc. of 17th International Scientific and Practical Conference (Odessa, May 23–27, 2016)). P. 125–126 .

  23. Rybalsky O.V., Soloviev V.I., Zhuravel V.V. Experimental verification of the effect of changes in the fractal composition of signals when editing a phonogram by cutting and rearranging fragments. Suchasna spetsialʹna tekhnika. 2016. N 3 (46). P. 75–85.

  24. Rybalsky O.V., Soloviev V.I., Zhuravel V.V. Basic requirements for the system for identifying digital editing points in phonograms and the methodology for its creation. Informatics and Mathematical Methods in Modeling. 2018. Vol. 8, N 3. P. 232–237.

  25. Yoshua Bengio. Deep learnning. Lxmls 2015. Machine Learnning Summer Shool. Lisbon, Portugal, 2015, 124 p. URL: http://www.iro.umontreal.ca/~bengioy/dlbook/.
Editorial Board Announcements Abstracts Authors Archive
about scope office editorial board instructions for authors subscriptions contacts
© 2020 Kibernetika.org. All rights reserved.