Speaker verification from partially encrypted compressed speech for forensic investigation

Authors:
L. A. Khan;Farkhund Iqbal;M. S. Baig
Affiliations:
Information Security Department, College of Telecom Engineering, NUST, Rawalpindi, Pakistan;Computer Security Laboratory, Faculty of Engineering and Computer Science, EV7.628 Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, Quebec, Canada H3G 1M8;Center for Advanced Studies in Engineering (CASE), Islamabad, Pakistan
Venue:
Digital Investigation: The International Journal of Digital Forensics & Incident Response
Year:
2010

Citing 6
Cited 0

Acoustical and environmental robustness in automatic speech recognition

Acoustical and environmental robustness in automatic speech recognition
Low power scalable encryption for wireless systems

Wireless Networks - Special issue VLSI in wireless networks
A tutorial on text-independent speaker verification

EURASIP Journal on Applied Signal Processing
The application of hidden Markov models in speech recognition

Foundations and Trends in Signal Processing
Spot Me if You Can: Uncovering Spoken Phrases in Encrypted VoIP Conversations

SP '08 Proceedings of the 2008 IEEE Symposium on Security and Privacy
Comparing maximum a posteriori vector quantization and Gaussian mixture models in speaker verification

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Speaker verification has recently been introduced to the forensic field as a new and complimentary approach to other forensic methods. With the advancement in speech communication technologies including voice over IP and wireless multimedia applications, speech is seldom sent between two parties in plain, it is at least partially encrypted before transmission. We present automatic speaker verification techniques based on hidden Markov and Gaussian mixture models from partially encrypted speech from the perceptually less relevant speech features which are unencrypted. An equal error rate (EER) of 23% and minimum detection cost value of 8% has been achieved on a database of 84 speakers using adapted Gaussian mixture modeling. Comparison between different modeling techniques and effect of Gaussian mixture densities are also carried out and results are tabulated. The results suggest that partial or selective encryption techniques may provide content protection but will not protect the speaker's identity.