Cancelable speaker verification system based on binary Gaussian mixtures

Biometrie systems suffer from non-revocabilty. In this paper, we propose a cancelable speaker verification system based on classical Gaussian Mixture Models (GMM) methodology enriched with the desired characteristics of revocability and privacy. The GMM model is transformed into a binary vector that is used by a shuffling scheme to generate a cancelable template and to guarantee the cancelabilty of the overall system. Leveraging the shuffling scheme, the speaker model can be revoked and another model can be reissued. Our proposed method enables the generation of multiple cancelable speaker templates from the same biometric modality that cannot be linked to the same user. The proposed system is evaluated on the RSR2015 databases. It outperforms the basic GMM system and experimentations show significant improvement in the speaker verification performance that achieves an Equal Error Rate (ERR) of 0.01%.

[1]  Christoph Busch,et al.  Biometric template protection for speaker recognition based on universal background models , 2015, IET Biom..

[2]  Sharath Pankanti,et al.  Biometric Recognition: Security and Privacy Concerns , 2003, IEEE Secur. Priv..

[3]  Pierre-Michel Bousquet,et al.  Speaker Modeling Using Local Binary Decisions , 2011, INTERSPEECH.

[4]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[5]  Dijana Petrovska-Delacrétaz,et al.  Cancelable Biometrics for Better Security and Privacy in Biometric Systems , 2011, ACC.

[6]  Larry P. Heck,et al.  MSR Identity Toolbox v1.0: A MATLAB Toolbox for Speaker Recognition Research , 2013 .

[7]  Anil K. Jain,et al.  Biometric Template Protection: Bridging the performance gap between theory and practice , 2015, IEEE Signal Processing Magazine.

[8]  Douglas A. Reynolds,et al.  A Tutorial on Text-Independent Speaker Verification , 2004, EURASIP J. Adv. Signal Process..

[9]  S. Kanade,et al.  Three factor scheme for biometric-based cryptographic key regeneration using iris , 2008, 2008 Biometrics Symposium.

[10]  Andreas Uhl,et al.  A survey on biometric cryptosystems and cancelable biometrics , 2011, EURASIP J. Inf. Secur..

[11]  Nalini K. Ratha,et al.  Generating Cancelable Fingerprint Templates , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[13]  Jean-François Bonastre,et al.  A novel speaker binary key derived from anchor models , 2010, INTERSPEECH.

[14]  Andrew Beng Jin Teoh,et al.  Secure speech template protection in speaker verification system , 2010, Speech Commun..

[15]  Madhu Sudan,et al.  A Fuzzy Vault Scheme , 2006, Des. Codes Cryptogr..

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

[17]  Wenhua Xu,et al.  Cancelable Voiceprint Template Based on Chaff-Points-Mixture Method , 2008, 2008 International Conference on Computational Intelligence and Security.

[18]  Nalini K. Ratha,et al.  Enhancing security and privacy in biometrics-based authentication systems , 2001, IBM Syst. J..

[19]  Dani Byrd,et al.  Phonetic analyses of word and segment variation using the TIMIT corpus of American english , 1994, Speech Commun..

[20]  Driss Matrouf,et al.  Discriminant binary data representation for speaker recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Bin Ma,et al.  Text-dependent speaker verification: Classifiers, databases and RSR2015 , 2014, Speech Commun..