Voice Passwords Revisited

We demonstrate an attack on basic voice authentication technologies. Specifically, we show how one member of a voice database can manipulate his voice in order to gain access to resources by impersonating another member in the same database. The attack targets a voice authentication system build around parallel and independent speech recognition and speaker verification modules and assumes that adapted Gaussian Mixture Model (GMM) is used to model basic Mel-frequency cepstral coefficients (MFCC) features of speakers. We experimentally verify our attack using the YOHO database. The experiments conclude that in a database of 138 users an attacker can impersonate anyone in the database with a 98% success probability after at most nine authorization attempts. The attack still succeeds, albeit at lower success rates, if fewer attempts are permitted. The attack is quite practical and highlights the limited amount of entropy that can be extracted from the human voice when using MFCC features.

[1]  Douglas D. O'Shaughnessy,et al.  Compensated mel frequency cepstrum coefficients , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[2]  Patrick Kenny,et al.  A Study of Interspeaker Variability in Speaker Verification , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  Patrick Kenny,et al.  Eigenvoice modeling with sparse training data , 2005, IEEE Transactions on Speech and Audio Processing.

[4]  Nikos Fakotakis,et al.  Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task , 2007 .

[5]  Larry P. Heck,et al.  On-line unsupervised adaptation in speaker verification , 2000, INTERSPEECH.

[6]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[7]  Qi Li,et al.  Cryptographic key generation from voice , 2001, Proceedings 2001 IEEE Symposium on Security and Privacy. S&P 2001.

[8]  Tomi Kinnunen,et al.  Spectral Features for Automatic Text-Independent Speaker Recognition , 2003 .

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

[10]  Larry P. Heck,et al.  An adaptive speaker verification system with speaker dependent a priori decision thresholds , 2002, INTERSPEECH.

[11]  Ran Gazit,et al.  SVM-based Speaker Classification in the GMM Models Space , 2006, 2006 IEEE Odyssey - The Speaker and Language Recognition Workshop.

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

[13]  Aaron E. Rosenberg,et al.  On the use of instantaneous and transitional spectral information in speaker recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Larry P. Heck,et al.  A model-based transformational approach to robust speaker recognition , 2000, INTERSPEECH.

[15]  Qi Li,et al.  Using voice to generate cryptographic keys , 2001, Odyssey.

[16]  Patrick Kenny,et al.  Joint Factor Analysis Versus Eigenchannels in Speaker Recognition , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[17]  Albert Strasheim.  AGNITIO's Speaker Recognition System for EVALITA 2009 , 2009 .

[18]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[19]  Hugh F. Durrant-Whyte,et al.  On entropy approximation for Gaussian mixture random vectors , 2008, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.