Speech authentication system using digital watermarking and pattern recovery |
| |
| Affiliation: | 1. Silicon Institute of Technology, Silicon Hills, Patia, Bhubaneswar 751024, Odisha, India;2. Department of Systems Engineering, Ajou University, San 5, Woncheon-dong, Yeongtong-gu, Suwon 443-749, South Korea;3. Soft Computing Laboratory, Department of Computer Science, Yonsei University, 134 Shinchon-dong, Sudaemoon-gu, Seoul 120-749, South Korea;4. Department of Industrial Engineering, Ajou University, San 5, Woncheon-dong, Yeongtong-gu, Suwon 443-749, South Korea;1. College of Information Engineering, Shenzhen University, Shenzhen 518060, China;2. College of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China;3. College of Mathematics and Information Science, Xinyang Normal University, Xinyang 464000, China;4. School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan 610031, China;1. Department of Electronic Engineering, National I-Lan University, Yi-Lan 26041, Taiwan, ROC;2. Department of Information Management, St. Mary’s Medicine, Nursing and Management College, Yi-Lan 26644, Taiwan, ROC;1. School of Information Science & Engineering, East China University of Science and Technology, 200237, China;2. Sino–US Global Logistics Institute, Antai College of Economics & Management, Shanghai Jiao Tong University, 200030, China |
| |
| 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 8 kHz and digitized at 16 bits resolution. Randomly chosen regions were substituted, removed, and compressed in MP3 at the rate of 16 kbps as well as in CELP at the rate of 11.5 kbps. The experiment shows the perfect detection for three kinds of forgeries and it proved the validity of the proposed method. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
