The development of communication technologies and the use of computer networks has led that the data is vulnerable to the violation. For this reason this paper proposed scrambling algorithm based on the Independent Component Analysis (ICA), and the descrambling process was achieved on Particle Swarm Optimization (PSO) to resolve this problem. In the scrambling algorithm, the one speech signals segmented into two types, two and three. It then used the mixing process to result the scrambling of speech. In the descrambling process, we proposed the kurtosis and negative entropies as fitness function. The simulation results indicate that the scrambled speech has no residual intelligibility, and the descrambled speech quality is satisfactory. The performance of scrambling algorithm has been tested on four metrics Signal to Noise Ratio (SNR), Perceptual Evaluation of Speech Quality and Mean Opinion Score (PESQ-MOS), Linear Predictive Coding (LPC) and itakura-saito distance. Many input speech signal of sampling frequency 16 kHz was tested for two genders male and female.

[1] Beker H. and Piper F., Secure Speech Communications, Academic Press, 1985.

[2] Bor R., “Real-time Noise Cancellation Using ICA-PSO-PE,” M.S. Thesis, Bilkent University, Gender Original Speech Scrambled Speech Recover Speech F1 F2 F3 M1 M2 M3 (16) 2 T 2c e c e cIS e c2 T 2e c c c e σ a R a σd (a ,a ) = + log - 1σ a R a σ              2c 2e 526 The International Arab Journal of Information Technology, Vol. 14, No. 4, July 2017 2012.

[3] Gao Y. and Xie S., “A Blind Source Separation Algorithm Using Particle Swarm Optimization,” in Proceeding of the IEEE 6th Circuits and Systems Symposium on Emerging Technologies: Frontiers of Mobile and Wireless Communication, Shanghai, pp. 297-300, 2004.

[4] Guo D. and Lin Q., “Fast Decryption Utilizing Correlation Calculation for BSS-based Speech Encryption System,” in Proceeding of 6th International Conference on Natural Computation, Yantai, pp. 1428-1432, 2010.

[5] Hussain I., Khanum A., Abbasi A., and Javed M., “A Novel Approach for Software Architecture Recovery using Particle Swarm Optimization,” The International Arab Journal of Information Technology, vol. 12, no.1, pp. 32-41, 2015.

[6] Igual J., Ababneh J., Llinares R., and Igual C., “Using Particle Swarm Optimization For Minimizing Mutual Information In Independent Component Analysis,” in Proceeding of 11th International Work-Conference on Artificial Neural Networks, Torremolinos, pp. 484-491, 2011.

[7] Igual J., Ababneh J., Llinares R., Miro-Borras J., and Zarzoso V., “Solving Independent Component Analysis Contrast Functions with Particle Swarm Optimization,” in Proceeding of International Conference on Artificial Neural Networks, Thessaloniki, pp. 519-524, 2010.

[8] Kennedy J. and Eberhart R., “Particle Swarm Optimization,” in Proceeding of the IEEE International Conference on Neural Networks, Perth, pp. 1942-1948, 1995.

[9] Li S., Li C., Lo K., and Chen G., “Cryptanalyzing an Encryption Scheme Based on Blind Source Separation,” IEEE Transactions on Circuits and Systems, vol. 55, no. 4, pp. 1055- 1063, 2008.

[10] Lin Q. and Yin F., “Blind Source Separation Applied To Image Cryptosystems with Dual Encryption,” Electronics Letter, vol. 38, no. 19, pp. 1092-1094, 2002.

[11] Lin Q. and Yin F., “Image Cryptosystems Based On Blind Source Separation,” in Proceeding of International Conference on Neural Networks and Signal Processing, Nanjing, pp. 1366-1369, 2003.

[12] Lin Q., Yin F., and Liang H., “A Fast Decryption Algorithm For BSS-Based Image Encryption,” in Proceeding of International Symposium on Neural Networks, Chengdu, pp. 318-325, 2006.

[13] Lin Q., Yin F., and Liang H., “Blind Source Separation-Based Encryption Of Images And Speeches,” in Proceeding of International Symposium on Neural Networks, Chongqing, pp. 544-549, 2005.

[14] Lin Q., Yin F., and Zheng Y., “Secure Image Communication Using Blind Source Separation,” in Proceeding of the IEEE 6th Circuits and Systems Symposium on Emerging Technologies: Frontiers of Mobile and Wireless Communication, Shanghai, pp. 261-264, 2004.

[15] Lin Q., Yin F., Mei T., and Liang H., “A Blind Source Separation Based Method for Speech Encryption,” IEEE Transactions on Circuits and Systems, vol. 53, no. 6, pp. 1320-1328, 2006.

[16] Lin Q., Yin F., Mei T., and Liang H., “A Speech Encryption Algorithm Based On Blind Source Separation,” in Proceeding of International Conference on Communications, Circuits and Systems, Chengdu, pp. 1013-1017, 2004.

[17] Matsunaga A., Koga K., and Ohkawa M., “An Analog Speech Scrambling System Using The FFT Technique With High-Level Security,” IEEE Journal on Selected Areas in Communications, vol. 7, no. 4, pp. 540-547, 1989.

[18] Nian F., Li W., Sun X., and Li M., “An Improved Particle Swarm Optimization Application to Independent Component Analysis,” Information Engineering and Computer Science, Wuhan, pp. 1-4, 2009.

[19] Oja E., Hyvarinen A., and Karhunen J., Independent Component Analysis, John Wiley and Sons, 2001.

[20] Quackenbush S., Barnwell T., and Clements M., Objective Measures of Speech Quality, Prentice- Hall, 1988.

[21] Sheu L., Chiou H., and Chen W., “Semi- One Time Pad Using Blind Source Separation for Speech Encryption,” International Journal of Computer, Electrical, Automation, Control and Information Engineering, vol. 5, no. 8, pp. 803- 806, 2011.

[22] Shi Y. and Eberhart R., “A Modified Particle Swarm Optimizer,” in Proceeding of the IEEE Congress on Evolutionary Computation, Anchorage, pp. 69-73, 1998.

[23] Xie L. and Jiang L., “Global Optimal ICA and its Application in Brain MEG Data Analysis,” in Proceeding of Conference Neural Networks and Brain, Beijing, pp. 353-357, 2005.

[24] Yang Z., Zhou G., Wu Z., and Zhang J., “New Method For Signal Encryption Using Blind Source Separation Based on Subband Decomposition,” Progress in Natural Science, vol. 18, no. 6, pp.751-755, 2008. Speech Scrambling based on Independent Component Analysis and Particle Swarm Optimization 527 Nidaa Abbas Completed her Doctoral degree from Computer Science Dept. in University of Technology, Iraq. She is a faculty member in the department of Software, IT faculty, University of Babylon. Her research areas include image processing, statistical signal processing, speech scrambling. Jahanshah Kabudian Completed his doctoral degree from AmirKabir University of Technology, (Tehran PolyTechnic), Iran. He is presently working as Ass. Professor, Department of Computer Engineering and Information Technology, Razi University, Iran. His areas of interest include Digital Signal Processing (DSP), Audio, Speech and Language Processing.