Watermarking Based on Compressive Sensing for Digital Speech Detection and Recovery †

In this paper, a novel imperceptible, fragile and blind watermark scheme is proposed for speech tampering detection and self-recovery. The embedded watermark data for content recovery is calculated from the original discrete cosine transform (DCT) coefficients of host speech. The watermark information is shared in a frames-group instead of stored in one frame. The scheme trades off between the data waste problem and the tampering coincidence problem. When a part of a watermarked speech signal is tampered with, one can accurately localize the tampered area, the watermark data in the area without any modification still can be extracted. Then, a compressive sensing technique is employed to retrieve the coefficients by exploiting the sparseness in the DCT domain. The smaller the tampered the area, the better quality of the recovered signal is. Experimental results show that the watermarked signal is imperceptible, and the recovered signal is intelligible for high tampering rates of up to 47.6%. A deep learning-based enhancement method is also proposed and implemented to increase the SNR of recovered speech signal.

[1]  Ahmed H. Tewfik,et al.  Robust audio watermarking using perceptual masking , 1998, Signal Process..

[2]  Banani Patra,et al.  CRT-based self-recovery watermarking technique for multimedia applications , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Gholamreza Anbarjafari,et al.  Imperceptible non-blind watermarking and robustness against tone mapping operation attacks for high dynamic range images , 2018, Multimedia Tools and Applications.

[4]  Jean-Francois Delaigle,et al.  Invisibility and application functionalities in perceptual watermarking an overview , 2002, Proc. IEEE.

[5]  Paschalis Tsiaflakis,et al.  Multiple Access Channel Optimal Spectrum Balancing for Upstream DSL Transmission , 2007, IEEE Communications Letters.

[6]  Akihiro Yamamoto,et al.  A digital watermark based on the wavelet transform and its robustness on image compression , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[7]  Asifullah Khan,et al.  Authentication and recovery of images using multiple watermarks , 2010, Comput. Electr. Eng..

[8]  Jiri Fridrich,et al.  Images with self-correcting capabilities , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[9]  Yousof Erfani,et al.  Robust audio watermarking using improved TS echo hiding , 2009, Digit. Signal Process..

[10]  Frank Y. Shih,et al.  Toral fragile watermarking for localizing and recovering tampered image , 2004, 2005 International Symposium on Intelligent Signal Processing and Communication Systems.

[11]  Fan Chen,et al.  A Fragile Watermarking Scheme for Audio Detection and Recovery , 2008, 2008 Congress on Image and Signal Processing.

[12]  Wenhuan Lu,et al.  Parameterization of LSB in Self-Recovery Speech Watermarking Framework in Big Data Mining , 2017, Secur. Commun. Networks.

[13]  Xinpeng Zhang,et al.  Fragile Watermarking Scheme with Extensive Content Restoration Capability , 2009, IWDW.

[14]  Xinpeng Zhang,et al.  Fragile Watermarking With Error-Free Restoration Capability , 2008, IEEE Transactions on Multimedia.

[15]  Jiashu Zhang,et al.  Adjacent-block based statistical detection method for self-embedding watermarking techniques , 2009, Signal Process..

[16]  Emin Anarim,et al.  Image Error Concealment Using Watermarking with Subbands for Wireless Channels , 2007, IEEE Communications Letters.

[17]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[18]  Ingemar J. Cox,et al.  Secure spread spectrum watermarking for multimedia , 1997, IEEE Trans. Image Process..

[19]  R. Eswaraiah,et al.  Robust medical image watermarking technique for accurate detection of tampers inside region of interest and recovering original region of interest , 2015, IET Image Process..

[20]  Indranil Sengupta,et al.  An adaptive audio watermarking based on the singular value decomposition in the wavelet domain , 2010, Digit. Signal Process..

[21]  Mauro Barni,et al.  DCT-based watermark recovering without resorting to the uncorrupted original image , 1997, Proceedings of International Conference on Image Processing.

[22]  Mário A. T. Figueiredo,et al.  Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems , 2007, IEEE Journal of Selected Topics in Signal Processing.

[23]  Nilanjan Dey,et al.  Stationary Wavelet Transformation Based Self-recovery of Blind-Watermark from Electrocardiogram Signal in Wireless Telecardiology , 2012, SNDS.

[24]  Chun-Shien Lu,et al.  Multipurpose watermarking for image authentication and protection , 2001, IEEE Trans. Image Process..

[25]  Joel A. Tropp,et al.  Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit , 2007, IEEE Transactions on Information Theory.

[26]  Fan Chen,et al.  Self-recovery Fragile Watermarking Scheme with Variable Watermark Payload , 2011, IWDW.

[27]  Nasir D. Memon,et al.  An SVD based audio watermarking technique , 2005, Proceedings of the IEEE 13th Signal Processing and Communications Applications Conference, 2005..

[28]  Nikolaos G. Bourbakis,et al.  An Efficient Packet Loss Recovery Methodology for Video Streaming Over IP Networks , 2009, IEEE Transactions on Broadcasting.

[29]  Shinfeng D. Lin,et al.  Dual watermark for image tamper detection and recovery , 2008, Pattern Recognit..

[30]  Chao-Ming Wu,et al.  A Simple Image Tamper Detection and Recovery Based on Fragile Watermark with One Parity Section and Two Restoration Sections , 2013 .

[31]  Anthony Tung Shuen Ho,et al.  A new semi-fragile image watermarking with robust tampering restoration using irregular sampling , 2007, Signal Process. Image Commun..

[32]  Tan Qi-xiang.  Technique of characteristic-based self-embedded watermark using in audio , 2007 .

[33]  Zhenxing Qian,et al.  Watermarking With Flexible Self-Recovery Quality Based on Compressive Sensing and Compositive Reconstruction , 2011, IEEE Transactions on Information Forensics and Security.

[34]  C. F. Osborne,et al.  A digital watermark , 1994, Proceedings of 1st International Conference on Image Processing.

[35]  Fathi E. Abd El-Samie,et al.  An efficient singular value decomposition algorithm for digital audio watermarking , 2009, Int. J. Speech Technol..

[36]  Zhenxing Qian,et al.  Reference Sharing Mechanism for Watermark Self-Embedding , 2011, IEEE Transactions on Image Processing.

[37]  Po-Whei Huang,et al.  A hierarchical digital watermarking method for image tamper detection and recovery , 2005, Pattern Recognit..