电信科学 ›› 2017, Vol. 33 ›› Issue (11): 93-101.doi: 10.11959/j.issn.1000-0801.2017277

• 研究与开发 • 上一篇    下一篇

基于比例因子转移概率的AAC音频压缩历史检测算法

黄其娟,王让定,严迪群   

  1. 宁波大学信息科学与工程学院,浙江 宁波 315211
  • 修回日期:2017-09-26 出版日期:2017-11-01 发布日期:2017-12-08
  • 作者简介:黄其娟(1993-),女,宁波大学信息科学与工程学院硕士生,主要研究方向为多媒体通信与信息安全等。|王让定(1962-),男,博士,宁波大学高等技术研究院教授、博士生导师,主要研究方向为多媒体通信与取证、信息隐藏与隐写分析、智能抄表及传感网络技术等。|严迪群(1979-),男,博士,宁波大学信息科学与工程学院副教授、硕士生导师,主要研究方向为多媒体通信、信息安全、基于深度学习的数字语音取证等。
  • 基金资助:
    国家自然科学基金资助项目(61672302);国家自然科学基金资助项目(61300055);浙江省自然科学基金资助项目(LZ15F020010);浙江省自然科学基金资助项目(Y17F020051);宁波大学科研基金资助项目(XKXL1405);宁波大学科研基金资助项目(XKXL1420);宁波大学科研基金资助项目(XKXL1509);宁波大学科研基金资助项目(XKXL1503);宁波大学王宽诚幸福基金资助项目

AAC compression detection based on scaling factor transition probability

Qijuan HUANG,Rangding WANG,Diqun YAN   

  1. College of Information Science and Engineering,Ningbo University,Ningbo 315211,China
  • Revised:2017-09-26 Online:2017-11-01 Published:2017-12-08
  • Supported by:
    The National Natural Science Foundation of China(61672302);The National Natural Science Foundation of China(61300055);Natural Science Foundation of Zhejiang Province of China(LZ15F020010);Natural Science Foundation of Zhejiang Province of China(Y17F020051);The Scientific Research Foundation of Ningbo University(XKXL1405);The Scientific Research Foundation of Ningbo University(XKXL1420);The Scientific Research Foundation of Ningbo University(XKXL1509);The Scientific Research Foundation of Ningbo University(XKXL1503);K.C.Wong Magna Fund in Ningbo University

摘要:

音频压缩历史的检测是音频取证的重要组成部分,对判断音频是否经过篡改和伪造有着十分重要的意义。通过研究发现,AAC音频比例因子的值会随着压缩次数的增加而逐渐减小。基于此,提出了一种基于比例因子转移概率差值统计特性的AAC音频压缩历史检测算法。实验结果表明,该算法能对多次压缩的AAC音频进行准确分类,其低码率转高码率间AAC音频平均分类准确率达到了99.75%,同码率间准确率达97.28%。另外,对比实验也证明了本文算法的性能优于现有算法。

关键词: AAC音频, 压缩历史, 比例因子, 转移概率

Abstract:

Audio compression history detection is an important part of audio forensics,which is important to detect whether audio has been tampered or forged.An algorithm of AAC audio compression history detection was presented by using the transition probability differences of scale factors as the discriminative feature.Experimental results demonstrate that the proposed method can distinguish the single,double and triple compressed AAC audios effectively,and from the low-bite-rate to high-bit-rate,the average classification accuracy achieves 99.75%,the same-bit-rate detection accuracy achieves 97.28%.In addition,the results of comparison experiments show that the proposed algorithm outperforms the state-of-the-art algorithm.

Key words: AAC audio, compression history, scale factor, transfer probability

中图分类号: 

No Suggested Reading articles found!