RADIOELECTRONIC AND COMPUTER SYSTEMS

It is created the system of recognition the steganographic-transformed voice commands of unmanned aerial vehicle control based on a cepstral analysis. It provides effective recognition and hidden commands transmission of to the board of an unmanned aerial vehicle, by converting voice control commands into a kind of steganographic characteristics vector, which implies the concealment of voice control information of an unmanned aerial vehicle. The mathematical model of the algorithm for calculating the mel-frequency cepstral coefficients and the recognition classifier of voice control commands for the solution of the problem of semantic identification and securing the control information of the unmanned aerial vehicle in the communication channel is synthesized. A software package has been developed that includes tools for compiling the base of reference voice images of subjects of management for training and testing the system for recognizing steganographic-transformed voice commands of the unmanned aerial vehicle control based on the cepstral analysis and computer models of the proposed methods and algorithms for recognition voice control commands in the MATLAB environment. The expediency of applying the proposed system for recognizing steganographic-transformed voice commands of the unmanned aerial vehicle control based on a cepstral analysis is substantiated and experimentally proved. An algorithm is presented for calculating the mel-frequency cepstral coefficients that appear in the role of the main features of recognition and the result of the steganographic transformation of speech, where for the evaluation of automatic recognition of voice commands using the results of classifier constructed by the criterion of minimum distance in the role which acts as the variance of the difference of the expectation of a mel-frequency cepstral coefficients. The obtained results of the experimental research allow to draw a conclusion about the expediency of further practical application of the developed system of recognition the steganographic-transformed voice commands of the unmanned aerial vehicle control based on the cepstral analysis

cepstral coefficients; Fourier transform; cosine transform; voice control system; unmanned aerial vehicle

Cuiling, L. English Speech Recognition Method Based on Hidden Markov Model. Smart Grid and Electrical Automation (ICSGEA), IEEE International Conference, 2016, pp. 94-97.

Lu, L., Renals, S. Small-Footprint Highway Deep Neural Networks for Speech Recognition. Transactions on Audio, Speech, and Language Pro-cessing, 2017, vol. 25, no. 7, pp. 1502-1511.

Hazem, Z. A study of speech recognition system based on the Hidden Markov Model with Gaussian-Mixture. Electrical Sciences and Technologies in Maghreb, IEEE International Conference, 2014, pp. 1-5.

Zhao, Y., Zhu, L. Speaker-Dependent Isolated-Word Speech Recognition System Based on Vector Quantization. Computer Network, Electronic and Automation (ICCNEA), IEEE International Conference, 2017, pp. 133-137.

Rashmi, N., Jyothi, K. An improved method for reversible data hiding steganography combined with cryptography. Inventive Systems and Control, IEEE 2nd International Conference, 2018, pp. 81-84.

Sharma, D., Sharma, De. Steganography of the keys into an encrypted speech signal using Matlab. Computing for Sustainable Global Development, IEEE 3rd International Conference, 2016, pp. 721-724.

Liu, J., Zhou, K., Tian, H. Least-significant-digit steganography in low bitrate speech. Communications, IEEE International Conference, 2012, pp. 1133-1137.

Lavrynenko, O., Konakhovych, G., Bakhtiiarov, D. Method of Voice Control Functions of the UAV. Methods and Systems of Navigation and Motion Control (MSNMC), IEEE 4th International Conference, 2016, pp. 47-50.

Lavrynenko, O.Yu., Konakhovych, G.F., Bakhtiiarov, D.I. Compression algorithm of voice control commands of UAV based on wavelet transform. Electronics and control systems, 2018, vol. 55, no. 1, pp. 17-22.