Application of neuron networks of deep learning for exposures editing of digital phonograms

Possibility of creation of effective system, which is intended for exposure of tracks of editing in digital phonograms and is built on the basis of neuron networks of the deep learning, is experimentally proven. Sense of experiment consisted in research of ability of the systems on the basis of such networks to expose pauses with tracks of editing. The experimental array of data is created in a voice editor from phonograms written on the different apparatus of the digital audio recording (at frequency of discretisation 44,1 kHz). A preselection of pauses was produced from it, having duration from 100 мs to a few seconds. From 1000 selected pauses the array of fragments of pauses is formed in the automatic (computer) mode, from which the arrays of fragments of pauses of different duration are generated by a dimension about 100 000. For forming of array of fragments of pauses with editing, the chosen pauses were divided into casual character parts in arbitrary correlation. Afterwards, the new pauses were created from it with the fixed place of editing. The general array of all fragments of pauses was broken into training and test arrays. The maximum efficiency, achieved on a test array in the process of educating, was determined. In general case this efficiency is determined by the maximum size of probability of correct classification of fragments with editing and fragments without editing. Scientifically reasonable methodology of exposure of signs of editing in digital phonograms is offered on the basis of neuron networks of the deep learning. The conducted experiments showed that the construction of the effective system is possible for the exposure of such tracks. Further development of methodology must be directed to find the ways to increase the probability of correct binary classification of investigated pauses.

neuron network of deep learning, points of editing, digital phonogram, digital editing, examination

1. Rybal’skii O. V. Substantive provisions of theory of exposure of tracks of digital treatment of phonograms and feature of her programmatic and methodical realization in examination of materials and facilities of the audio videorecording. Part 1. Zakhyist informatsii = Ukrainian Information Security Research Journal, 2006, no. 1, pp. 71–76 (in Russian).

2. Nicolalde D. P., Apolinario J. A. Evaluating digital audio authenticity with spectral distances and ENF phase change. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, vol. 1, pp. 1417–1420. https:// doi.ieeecomputersociety.org/10.1109/ICASSP.2009.4959859

3. 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, pp. 534–543. https://doi. org/10.1109/TIFS.2010.2051270

4. Korycky R. Methods of Time-Frequency Analysis in Authentication of Digital Audio Recordings. INTL Journal of Electronics and Telecommunications, 2010, vol. 56, no. 3, pp. 257–262. https://doi.org/10.2478/v10177-010-0033-0

5. Bobritskii S. M., Storozhenko S. V. Research of signs of editing of the records executed by digital record devices. Teoriya ta praktyka sudovoyi ecspertyzy i criminalistiki: zbirnik naukovikh prats [Theory and Practice of Forensic Science and Criminology: Collection of Scientific Papers]. Kharkov, Pravo Publ., 2011, Issue 11, pp. 353–361 (in Ukrainian).

6. Zhuravel’ V. V. Features of forming of phonograms writtenin from telephone channels. Suchasna spetsialna tehnika [Modern Special Technoque], 2015, no. 4, pp. 26–31 (in Russian).

7. Lozhkevich A. A., Snetkov V. A., Chivanov V. A., Sharshunskii V. L. Bases of Expert Criminalistics Research of Magnetic Phonograms. Moscow, All-Union Scientific Research Institute of the USSR Ministry of Internal Affairs, 1972. 172 p. (in Russian).

8. Rybal’skii O. V. Models of non-standard imitation of digital phonograms. Regestratsiya, zberigannya i obrobka danykh = Data Recording, Storage and Processing, 2003, no. 4, pp. 25–32 (in Russian).

9. Rybal’skii O. V., Solov’ev V. I., Zhuravel’ V. V. Tracks of editing are in digital phonograms, excision and transposition of fragments executed by a method. Regestratsiya, zberigannya i obrobka danykh = Data Recording, Storage and Processing, 2016, no. 1, pp. 32–41 (in Russian).

10. Rybal’skii O. V., Solov’ev V. I., Zhuravel’ V. V. Experimental verification of effect of change of fractal composition of signals at editing of phonogram the method of excision and transposition of fragments. Suchasna spetsialna tekhnika [Modern Special Technoque], 2016, no. 3, pp. 75–85 (in Russian).

11. Rybal’skii O. V., Solov’ev V. I., Zhuravel’ V. V. Basic requirements to the system of exposure of points of the digital editing in phonograms and methodology of her creation. Informatica ta matematichi metody v modeluvanni = Informatics and Mathematical Methods in Simulation, 2018, vol. 8, no. 3, pp. 232–237 (in Russian).