Speaker identification security improvement by means of speech watermarking

• Published in: Pattern recognition Vol. 40; no. 11; pp. 3027 - 3034
• Main Authors: Faundez-Zanuy, Marcos, Hagmüller, Martin, Kubin, Gernot
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.11.2007; Elsevier Science
• Subjects: Applied sciences; Biometrics; Cryptography; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Image processing; Information, signal and communications theory; Security; Signal and communications theory; Signal processing; Signal, noise; Speech processing; Speech watermark; Telecommunications and information theory; Biometrics; Security; Speech watermark; Acoustic signal; Image processing; Mixture theory; Forensic aspect; Digital recording; Pattern recognition; Speaker recognition; Gaussian process; Vocal signal; Information protection; System identification; Safety; Automatic recognition; Speech processing; Digital watermarking
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2007.02.016

This paper presents a security enhanced speaker identification system based on speech signal watermarking. Our proposed system can detect several situations where a playback speech, a synthetically generated speech, or a hacker trying to imitate the speech is fooling the biometric system. It is also suitable for forensic experts, who sometimes have to demonstrate in front of a court that a digital recording has neither been manipulated nor edited. In addition, we demonstrate that this watermark can coexist simultaneously with biometric speaker identification based on Gaussian mixture models (GMM), minimizing the mutual effects.