Speaker verification security improvement by means of speech watermarking

Authors:
Marcos Faundez-Zanuy;Martin Hagmüller;Gernot Kubin
Affiliations:
Escola Universitaria Politècnica de Mataró, Telecommunication, Avda. Puig i Cadafalch 101-111, 08303 Mataro, Barcelona, Spain;Graz University of Technology, Signal Processing and Speech Communication Laboratory, Inffeldgasse 12, 8010 Graz, Austria;Graz University of Technology, Signal Processing and Speech Communication Laboratory, Inffeldgasse 12, 8010 Graz, Austria
Venue:
Speech Communication
Year:
2006

Citing 5
Cited 6

Techniques for data hiding

IBM Systems Journal
AHUMADA: A large speech corpus in Spanish for speaker characterization and identification

Speech Communication - Speaker recognition and its commercial and forensic applications
Discrete Time Processing of Speech Signals

Discrete Time Processing of Speech Signals
Spread spectrum signaling for speech watermarking

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Exploring Steganography: Seeing the Unseen

Computer

Speaker identification security improvement by means of speech watermarking

Pattern Recognition
A reversible acoustic steganography for integrity verification

IWDW'10 Proceedings of the 9th international conference on Digital watermarking
Digital watermarking: new speech and image applications

NOLISP'09 Proceedings of the 2009 international conference on Advances in Nonlinear Speech Processing
Editorial: An overview of information fusion in the domain of watermarking and document security

Information Fusion
Speech authentication by semi-fragile speech watermarking utilizing analysis by synthesis and spectral distortion optimization

Multimedia Tools and Applications
An overview of digital speech watermarking

International Journal of Speech Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a security enhanced speaker verification system based on speech signal watermarking. Our proposed system can detect several situations where a playback speech, a synthetically generated speech, a manipulated speech signal or a hacker trying to imitate the speech is fooling the biometric system. In addition, we have generated a watermarked speech signals database from which we have obtained relevant conclusions about the influence of this technique on speaker verification rates. Mainly we have checked that biometrics and watermarking can coexist simultaneously minimizing the mutual effects. Experimental results show that the proposed speech watermarking system can suffer A-law coding with a message error rate lower than 2x10^-^4 for SWR higher than 20dB at a message rate of 48bits/s.