Biometric voice authentication auto-evaluation system

Authentication that is based on Biometrics traits is more secure for many applications like cryptosystems, therefore; the template of stored biometric members of the biometric authentication system is a dangerous issue, while it can be stolen or breached. We produce in this paper an automatic evaluator depending on the biometric performance measures FAR, FRR and EER by simulating how noise in the transmission and background environment may have effect on the voice signals in the biometric template. Many types of research focused on just the rate of the FAR, FRR and ERR of the authentication system that can produce. This paper introduce a new view of how to see the database template from the statistical side depending on biometric performance measures. We test our new view by producing an evaluator system and perform it on the TIMIT speech database by using AWGN to simulate white noise in the transmission and background environment with deferent SNR levels. We found -from the empirical method- promising results and we hope that this paper spots some light on how to evaluate biometric voice template automatically and providing a report about expected accuracy and security.

[1]  Foster J. Provost,et al.  ROC confidence bands: an empirical evaluation , 2005, ICML.

[2]  Sofus A. Macskassy,et al.  Pointwise ROC Confidence Bounds: An Empirical Evaluation , 2005 .

[3]  Anil K. Jain,et al.  Biometric Template Security , 2008, EURASIP J. Adv. Signal Process..

[4]  Rabul Hussain Laskar,et al.  Study on biometric authentication systems, challenges and future trends: A review , 2013 .

[5]  John H. L. Hansen,et al.  Getting started with SUSAS: a speech under simulated and actual stress database , 1997, EUROSPEECH.

[6]  Jiankun Hu,et al.  A New Biocryptosystem-Oriented Security Analysis Framework and Implementation of Multibiometric Cryptosystems Based on Decision Level Fusion , 2015, IEEE Transactions on Information Forensics and Security.

[7]  Carlisle M. Adams,et al.  You are the key: Generating cryptographic keys from voice biometrics , 2010, 2010 Eighth International Conference on Privacy, Security and Trust.

[8]  Anil K. Jain,et al.  Biometric cryptosystems: issues and challenges , 2004, Proceedings of the IEEE.

[9]  Dipak M. Adhyaru,et al.  A survey of automated biometric authentication techniques , 2013, 2013 Nirma University International Conference on Engineering (NUiCONE).

[10]  J. L. Wayman,et al.  Best practices in testing and reporting performance of biometric devices. , 2002 .

[11]  Carla Lopes,et al.  Phone Recognition on the TIMIT Database , 2012 .

[12]  Christoph Busch,et al.  Multi-Bit Allocation: Preparing Voice Biometrics for Template Protection , 2016, Odyssey.

[13]  Saleh Mesbah,et al.  Improving speaker identification system using discrete wavelet transform and AWGN , 2014, 2014 IEEE 5th International Conference on Software Engineering and Service Science.

[14]  Chengwei Huang,et al.  Speech Emotion Recognition under White Noise , 2013 .

[15]  Daniel P. Lopresti,et al.  Toward Speech-Generated Cryptographic Keys on Resource-Constrained Devices , 2002, USENIX Security Symposium.

[16]  Arun Ross,et al.  Biometric template security: Challenges and solutions , 2005, 2005 13th European Signal Processing Conference.

[17]  Anil K. Jain,et al.  Biometric Systems: Technology, Design and Performance Evaluation , 2004 .

[18]  Michael K. Reiter,et al.  Towards practical biometric key generation with randomized biometric templates , 2008, CCS.

[19]  Daniel P. Lopresti,et al.  Speech biometric mapping for key binding cryptosystem , 2011, Defense + Commercial Sensing.

[20]  Tsuyoshi Isshiki,et al.  Narrow Fingerprint Sensor Verification with Template Updating Technique , 2012, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[21]  Jordi Solé i Casals,et al.  Mathematical Morphology Preprocessing to Mitigate AWGN Effects: Improving Pitch Tracking Performance in Hard Noise Conditions , 2009, NOLISP.

[22]  Foster J. Provost,et al.  Confidence Bands for Roc Curves , 2004, ROCAI.

[23]  Drottning Kristinas.  DATABASES FOR SPEAKER RECOGNITION : ACTIVITIES IN COST 250 WORKING GROUP 2 , 1999 .