Watermarking Based on Compressive Sensing for Digital Speech Detection and Recovery (†).
Watermarking Based on Compressive Sensing for Digital Speech Detection and Recovery (†).
复制标题
基于压缩感知的数字语音检测和恢复的水印
DOI：
10.3390/s18072390
复制
发表时间：
2018-07-23
期刊：
影响因子：
--
通讯作者：
Dang J
中科院分区：
文献类型：
--
作者：
Lu W;Chen Z;Li L;Cao X;Wei J;Xiong N;Li J;Dang J
提出了一种新的用于语音篡改检测和自恢复的不可感知、脆弱的盲水印方案。用于内容恢复的嵌入水印数据从宿主语音的原始离散余弦变换（DCT）系数计算。水印信息在帧组中共享，而不是存储在一个帧中。该方案在数据浪费问题和篡改重合问题之间进行了权衡。当嵌入水印的语音信号的一部分被篡改时，可以准确地定位篡改区域，在没有任何修改的情况下仍然可以提取出该区域中的水印数据。然后利用DCT域的稀疏性，采用压缩感知技术来恢复系数。篡改区域越小，恢复信号的质量越好。实验结果表明，嵌入水印后的信号是不可感知的，恢复后的信号是可理解的，篡改率高达47.6%。还提出并实现了一种基于深度学习的增强方法，以提高恢复语音信号的信噪比。
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.
登录
查看更多内容
影响因子：
2.9
作者：
Erfani, Yousof;Siahpoush, Shadi
通讯作者：
Siahpoush, Shadi
影响因子：
2.5
作者：
Tropp, Joel A.;Gilbert, Anna C.
通讯作者：
Gilbert, Anna C.
影响因子：
4.4
作者：
Swanson, MD;Zhu, B;Boney, L
通讯作者：
Boney, L
影响因子：
10.6
作者：
Cox, IJ;Kilian, J;Shamoon, T
通讯作者：
Shamoon, T
影响因子：
2.9
作者：
Bhat, Vivekananda K.;Sengupta, Indranil;Das, Abhijit
通讯作者：
Das, Abhijit