Speaker Identity Tracing Scheme in 5G Communication Based on Fingerprint

doi:10.3969/j.issn.1671-1122.2021.03.010

Abstract

Abstract:

With the widespread popularization and application of 5G communication technology, concerns about security issues of 5G communication system are rising. To solve the difficulty of identity tracing caused by counterfeiting, forging or denying of speaker identity, in this article, a speaker identity tracing scheme for 5G remote communication is proposed. The biometric fingerprint information of speaker has been acquired from smartphone before calling. During the calling, the biometric fingerprint information which represents speaker identity is embedded into the voice signal using digital watermarking technology, thus the relevance between the speaker identity and the speech is established. Once the speaker identity is queried, it can be traced by extracting the biometric fingerprint information from speech signal. The performance of extracting fingerprint from speech which contains fingerprint information and is transferred through wireless channel after modulated by Generalized Frequency Division Multiplexing is presented. The simulation results show that, the fingerprint extraction performance of the scheme in 5G modulated by Generalized Frequency Division Multiplexing outperforms than that in 4G communication system, and it has potential application worth for preventing telecommunication fraud in the next generation of mobile communication.

Key words: 5G security, GFDM, identity tracing, digital watermarking

CLC Number:

TP309

SHANG Wen, WANG Hongxia. Speaker Identity Tracing Scheme in 5G Communication Based on Fingerprint[J]. Netinfo Security, 2021, 21(3): 79-86.

Figures/Tables 10

References 15

[1]	ZHENG Linlin, LI Jiakang, SUN Meng, et al. When Automatic Voice Disguise Meets Automatic Speaker Verification[J]. IEEE Transactions on Information Forensics and Security, 2020,16(9):824-837.
[2]	CAO Wencheng, WANG Hongxia, ZHAO Hong, et al. Identification of Electronic Disguised Voices in the Noisy Environment [C]//IWDW. 15th International Workshop, September 17-19, 2016, Beijing, China. Berlin: Springer, 2016: 75-87.
[3]	MENG Z, ALTAF M U B, JUANG B H. Active Voice Authentication[J]. Digital Signal Processing, 2020,101(1):1-12.
[4]	BARLASKAR S A, LASKAR M A, SHOME N, et al. Study on the Varying Degree of Speaker Identity Information Reflected Across the Different MFCCs [C]//IEEE. 2016 International Conference on Inventive Computation Technologies (ICICT), August 26-27, 2016, Coimbatore, India. New York: IEEE, 2016: 1-6.
[5]	ZENG Chunyan, MA Chaofeng, WANG Zhifeng, et al. A Robust Speaker Recognition Method Based on Convolutional Neural Network[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2020,48(6):39-44.
	曾春艳, 马超峰, 王志锋, 等. 基于卷积神经网络的鲁棒性说话人识别方法[J]. 华中科技大学学报(自然科学版), 2020,48(6):39-44.
[6]	LU Xiaoxuan, WEN Hongkai, WANG Sen, et al. SCAN: Learning Speaker Identity from Noisy Sensor Data [C]//IEEE. 2017 16th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), April 18-21, 2017, Pittsburgh, PA. New York: IEEE, 2017: 67-78.
[7]	WANG Hongxia, SANG Jing. Speaker Identity Tracing Using Fingerprint Data Hiding Against Telecommunications Fraud [C]//IEEE. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), November 12-15, 2018, Honolulu, HI. USA. New York: IEEE, 2018: 554-559.
[8]	FETTWEIS G, KRONDORF M, BITTNER S. GFDM-generalized Frequency Division Multiplexing [C]//IEEE. VTC Spring 2009-IEEE 69th Vehicular Technology Conference, April 26-29, 2019, Barcelona, Spain. New York: IEEE, 2009: 1-4.
[9]	MICHAILOW N, MATTHE M, GASPAR I S, et al. Generalized Frequency Division Multiplexing for 5th Generation Cellular Networks[J]. IEEE Transactions on Communications, 2014,62(9):3045-3061.
[10]	BANDARI S K, MANI V V, DROSOPOULOS A. OQAM Implementation of GFDM [C]//IEEE. 2016 23rd International Conference on Telecommunications (ICT), May 16-18, 2016, Thessaloniki, Greece. New York: IEEE, 2016: 1-5.
[11]	Database I-TGV and Audio. ITU-T Test Signals for Telecommunication Systems[EB/OL]. http://www.itu.int/net/itu-t/sigdb/speaudio/Gseries.htm, 2020-09-15.
[12]	MALTONI D, MAIO D, JAIN A K, et al. FVC2000 Database[EB/OL]. http://bias.csr.unibo.it/fvc2000/download.asp, 2020-09-19.
[13]	MICHAILOW N, KRONE S, LENTMAIER M, et al. Bit Error Rate Performance of Generalized Frequency Division Multiplexing [C]//IEEE. 2012 IEEE Vehicular Technology Conference (VTC Fall), September 2-6, 2012, Quebec City, QC, Canada. New York: IEEE, 2012: 1-5.
[14]	PITCHAIAH T, YARRABOTHU R S. Performance Analysis of OQAM Based GFDM 5G Systems Under Line of Sight Fading Scenarios [C]//IEEE. 2017 International Conference on Intelligent Sustainable Systems (ICISS), December 7-8, 2017, Palladam, India. New York: IEEE, 2017: 602-606.
[15]	TELAGATHOTI P, YARRABOTHU R S. Performance of OQAM Based GFDM under Real-time Fading Conditions[J]. International Journal of Recent Technology and Engineering. 2019,7(5):224-228.

参数	参数变量	设置值
子载波数量	K	2048
时域段数量/子符号数量	M	8
数据块数量	B	19
脉冲整形波形	g	RC
滚降因子	$\alpha $	0.1
调制系数	$\mu $	4
循环前缀长度	Ncp	10