一种基于奇偶相关性网络的基音周期隐写分析方法  

A Steganographic Analysis Method for Fundamental Tone Period Based on Parity Correlation Networks

作　　者：王嘉伟 楼芊驿 戴望宇 杨洁 WANG Jiawei;LOU Qianyi;DAI Wangyu;YANG Jie(College of Engineering and Technology,Jiyang College of Zhejiang A&F University,Shaoxing 311800,China)

机构地区：[1]浙江农林大学暨阳学院工程技术学院,浙江绍兴311800

出　　处：《现代信息科技》2023年第20期92-95,99,共5页Modern Information Technology

基　　金：国家级大学生创新创业训练计划项目(202213283001);浙江农林大学暨阳学院科研训练计划资助项目(JYKC2205)。

摘　　要：由于基音周期参数在语音编码过程中具有不可预测性,因此,很多隐写算法都将隐藏信息嵌入到基音周期中。目前已有多种基于基音周期的检测方法,但是如何准确的做到信息隐藏检测仍是一项挑战。文章提出了一种基于奇偶相关性网络的基因周期隐写分析方法。实验结果表明,该方法可以有效地检测基于基音周期的隐写术。实验结果表明,提出的方法可以有效地检测基于基音周期的隐写术,具有良好的实时性和健壮性。Due to the unpredictability of fundamental tone period parameters during the speech coding process,many steganographic algorithms embed hidden information into fundamental tone period.At present,there are many detection methods based on fundamental tone period,but how to accurately detect information hiding is still a challenge.In this paper,a steganographic analysis method for fundamental tone period based on parity correlation network is proposed.Experimental results show that the proposed method can effectively detect steganography based on fundamental tone period,and has good real-time performance and robustness.

关 键 词：信息隐藏检测 SVM 语音码流 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]