一种基于线性预测系数多级矢量量化的语音零水印  

Audio Zero Watermark Based on Multi-level Vector Quantization of Linear Predictive Coding Coefficient

作　　者：郑锦波[1] 张贵仓[1] 

机构地区：[1]西北师范大学数学与信息科学学院,甘肃兰州730070

出　　处：《佳木斯大学学报（自然科学版）》2010年第5期728-731,共4页Journal of Jiamusi University：Natural Science Edition

基　　金：教育部重点科学技术项目

摘　　要：提出一种基于线性预测系数多级矢量量化的数字零水印算法.通过对语音信号的线性预测系数进行多级矢量量化与待嵌入水印进行异或得到检测密钥,并在接收端进行盲水印提取.实验结果证明,该算法对于各种攻击尤其对幅度缩放、低通滤波和音量标准化具有较好的鲁棒性和不可见性.An audio zero watermark based on the Multi-level Vector Quantization of linear predictive coding coefficient method was proposed.In the proposed method,the key with the method that the robust watermark was embedded in the Multi-level Vector Quantization of linear predictive coding coefficient which is picked up from the audio and index constrained respectively.Simulation results demonstrated that the effectiveness of the proposed algorithm in terms of robustness and imperceptibility was excellent especially in amplitude scaling,low-pass filter and volume normalization.

关 键 词：数字零水印 多级矢量量化 鲁棒性 版权确认 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]