Speech authentication system using digital watermarking and pattern recovery

Authors:
Chang-Mok Park;Devinder Thapa;Gi-Nam Wang
Affiliations:
Department of Industrial and Information System Engineering, AJOU University, San 5, Woncheon-dong, Yeongtong-gu, Suwon 442-749, South Korea;Department of Industrial and Information System Engineering, AJOU University, San 5, Woncheon-dong, Yeongtong-gu, Suwon 442-749, South Korea;Department of Industrial and Information System Engineering, AJOU University, San 5, Woncheon-dong, Yeongtong-gu, Suwon 442-749, South Korea
Venue:
Pattern Recognition Letters
Year:
2007

Citing 5
Cited 6

Robust audio watermarking using perceptual masking

Signal Processing
Echo Hiding

Proceedings of the First International Workshop on Information Hiding
Detecting Digital Forgeries Using Bispectral Analysis

Detecting Digital Forgeries Using Bispectral Analysis
Robust spread-spectrum audio watermarking

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Secure spread spectrum watermarking for multimedia

IEEE Transactions on Image Processing

An integrated on-line audio watermark decoding scheme for broadcast monitoring

Multimedia Tools and Applications
Audio Watermarking Based on Advanced Wigner Distribution and Important Frequency Peaks

International Journal of High Performance Computing Applications
A robust content based audio watermarking using UDWT and invariant histogram

Multimedia Tools and Applications
On the music content authentication

Proceedings of the 20th ACM international conference on Multimedia
Speech authentication by semi-fragile speech watermarking utilizing analysis by synthesis and spectral distortion optimization

Multimedia Tools and Applications
A novel speech content authentication algorithm based on Bessel-Fourier moments

Digital Signal Processing

Quantified Score

Hi-index	0.10

Visualization

Abstract

The objective of this paper is to detect speech forgery using digital audio watermarking and pattern recovery techniques. A digital watermark pattern has been attached with the speech signal to detect three kinds of alterations or forgeries such as substitution, insertion, and removal. The watermark pattern will be modified if some changes have been made to the speech contents. Modification and forgery can be measured and detected by pattern recovery. The proposed method uses the cyclic pattern embedding to overcome synchronizing problems of previous detection techniques. In addition, pattern recovery enhances the robustness to compression. This method has been tested and verified using six recording devices, which was used for collecting verbal data. The speech signals were sampled at the rate of 8kHz and digitized at 16bits resolution. Randomly chosen regions were substituted, removed, and compressed in MP3 at the rate of 16kbps as well as in CELP at the rate of 11.5kbps. The experiment shows the perfect detection for three kinds of forgeries and it proved the validity of the proposed method.