电子学报

• •    

基于多特征融合和BiLSTM的语音隐写检测算法

苏兆品1,2,3,4, 张羚1, 张国富1,2,3,4, 岳峰1,4   

  1. 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
  • 收稿日期:2022-06-15 修回日期:2022-06-15 出版日期:2022-07-13
    • 作者简介:
    • 苏兆品 女, 1983年8月出生于山东省菏泽市.现为合肥工业大学计算机与信息学院副教授、 硕士生导师.获安徽省自然科学奖1项.在国内外发表学术论文40余篇. E-mail: szp@hfut.edu.cn
      张 羚 女, 1995年4月出生于甘肃省武威市.硕士研究生, 主要研究方向为音频隐写和隐写分析.E-mail: 1772950753@qq.com
      张国富(通讯作者) 男, 1979年3月出生于安徽省合肥市.现为合肥工业大学计算机与信息学院教授、 硕士生导师.主要研究方向为联盟博弈、 进化计算、 音频安全.
      岳 峰 男, 1981年2月出生于安徽省合肥市.现为合肥工业大学计算机与信息学院副研究员、 硕士生导师.主要研究方向为软件工程、信息安全.E-mail: yuefeng@hfut.edu.cn
    • 基金资助:
    • 安徽省重点研究与开发计划 (202004d07020011); 教育部人文社会科学研究青年基金项目 (19YJC870021); 广东省类脑智能计算重点实验室开放课题 (GBL202117); 中央高校基本科研业务费专项资金项目 (PA2021GDSK0073)

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

SU Zhao-pin1,2,3,4, ZHANG Ling1, ZHANG Guo-fu1,2,3,4, YUE Feng1,4   

  1. 1.School of Computer Science and Information Engineering,Hefei University of Technology,Hefei,Anhui 230601,China
    2.Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology),Ministry of Education,Hefei,Anhui 230601,China
    3.Intelligent Interconnected Systems Laboratory of Anhui Province(Hefei University of Technology),Hefei,Anhui 230009,China
    4.Anhui Province Key Laboratory of Industry Safety and Emergency Technology(Hefei University of Technology),Hefei,Anhui 230601,China
  • Received:2022-06-15 Revised:2022-06-15 Online:2022-07-13

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.

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

Abstract:

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 algorithm based on the multi-feature fusion and the bi-directional long short-term memory(BiLSTM) network is proposed. Specifically, the impact of steganography on iLBC parameters is first analyzed in the linear spectrum frequency coefficient vector quantization process, the dynamic codebook search process, and the gain quantization process. Then, multiple steganographic features in the above three stages are extracted and input to three different detection models based on BiLSTM, respectively. 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.

Key words: joint steganalysis, internet low bit rate codec, bi-directional long short-term memory network, steganographic feature extraction, multi-feature fusion

中图分类号: