基于多特征融合和BiLSTM的语音隐写检测算法  

A Speech Steganalysis Algorithm Based on Multi-Feature Fusion and BiLSTM

作　　者：苏兆品[1,2,3,4] 张羚 张国富 岳峰[1,4] SU Zhao-pin;ZHANG Ling;ZHANG Guo-fu;YUE Feng(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei,Anhui 230601,China;Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology),Ministry of Education,Hefei,Anhui 230601,China;Intelligent Interconnected Systems Laboratory of Anhui Province(Hefei University of Technology),Hefei,Anhui 230009,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology(Hefei University of Technology),Hefei,Anhui 230601,China)

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230601 [2]大数据知识工程教育部重点实验室(合肥工业大学),安徽合肥230601 [3]智能互联系统安徽省实验室(合肥工业大学),安徽合肥230009 [4]工业安全应急技术安徽省重点实验室(合肥工业大学),安徽合肥230601

出　　处：《电子学报》2023年第5期1300-1309,共10页Acta Electronica Sinica

基　　金：安徽省重点研究与开发计划(No.202004d07020011,No.202104d07020001);教育部人文社会科学研究青年基金项目(No.19YJC870021);广东省类脑智能计算重点实验室开放课题(No.2020B121201001);中央高校基本科研业务费专项资金项目(No.PA2021GDSK0073,No.PA2021GDSK0074)。

摘　　要：针对传统互联网低比特率编解码器(internet Low Bit Rate Codec,iLBC)语音隐写主要集中在线性频谱频率系数矢量量化、码本搜索矢量量化或增益量化的单个阶段,难以应对多阶段下的联合隐写检测等问题,提出一种基于多特征融合和双向长短时记忆(Bi-Directional Long Short-Term Memory,BiLSTM)网络的iLBC语音隐写检测算法.通过分析隐写对不同阶段参数带来的影响,提取线性频谱频率系数矢量量化、码本搜索矢量量化和增益量化过程中的多种隐写特征,并分别输入到相应的BiLSTM检测网络,最后将各检测网络的结果进行融合,得到最终隐写检测结果 .实验表明,所提算法可以实现多阶段下的联合隐写检测,而且在语音时长较短时,仍能取得优异的检测结果,平均检测准确率达到了90%以上.The traditional internet low bit rate codec(iLBC)based speech steganography mainly focuses on a single stage of the linear spectrum frequency coefficient vector quantization,the codebook search vector quantization,or the gain quantization,which is difficult to deal with the multi-stage joint steganalysis.To this end,an iLBC speech steganalysis algo-rithm based on the multi-feature fusion and the bi-directional long short-term memory(BiLSTM)network is proposed.Spe-cifically,the impact of steganography on iLBC parameters is first analyzed in the linear spectrum frequency coefficient vec-tor quantization process,the dynamic codebook search process,and the gain quantization process.Then,multiple stegano-graphic features in the above three stages are extracted and input to three different detection models based on BiLSTM,re-spectively.Finally,a fusion strategy is presented to merge the detection results of each model.Experimental results show that the proposed algorithm can achieve multi-stage joint steganalysis and good detection results with an average detection accuracy of more than 90%,even if the speech duration is short.

关 键 词：联合隐写检测 互联网低比特率编解码器 双向长短时记忆网络 隐写特征提取 多特征融合 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]