[1]林晓丹.采用线性预测模型的语音篡改检测[J].华侨大学学报(自然科学版),2015,36(1):40-44.[doi:10.11830/ISSN.1000-5013.2015.01.0040]
　LIN Xiao-dan.Speech Forgeries Detection with Linear Prediction Model[J].Journal of Huaqiao University(Natural Science),2015,36(1):40-44.[doi:10.11830/ISSN.1000-5013.2015.01.0040]
点击复制

采用线性预测模型的语音篡改检测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第1期
页码:
40-44
栏目:
出版日期:
2015-01-20

文章信息/Info

Title:
Speech Forgeries Detection with Linear Prediction Model
文章编号:
1000-5013(2015)01-0040-05
作者:
林晓丹
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
LIN Xiao-dan
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
篡改检测;  线性预测模型;  超高斯;  高阶统计特征
Keywords:
forgery detection;  linear prediction model;  super gaussian;  higher order statistics
分类号:
TP309
DOI:
10.11830/ISSN.1000-5013.2015.01.0040
文献标志码:
A
摘要:
基于线性预测模型,提出一种通用的语音信号真实性和完整性的鉴别方法.将线性预测残差信号通过带通滤波器,消除谐波信号分量的干扰.滤波后的原始语音残差信号呈高斯分布,而篡改语音的残差则体现出明显的超高斯特性,将预测残差的高阶统计特征作为判断篡改的依据.实验结果表明:该方法能够有效实现语音篡改盲检测,并定位篡改位置;在噪声环境下,与现有方法相比,文中的检测方法具有更高的鲁棒性.
Abstract:
Based on linear prediction model, a general forensic approach aiming to ensure the authenticity and integrity of speech is presented. To eliminate the influence of harmonic components existed in the LPC residual, a band-pass filter is introduced. The original speech residual follows a Gaussian distribution while its forgery counterpart shows a super Gaussian characteristic. Higher order statistics of the LPC residual is applied to forgery detection. Experimental results show the effectiveness of our method in detecting and locating forgery. Results also demonstrate the higher robustness of our detection method in noise environment compared to the state-of-the-art method.

参考文献/References:

[1] SWATI G,SEONGHO C,KUO C C J.Current developments and future trends in audio authentication[J].IEEE Multimedia,2012,19(1):50-59.
[2] LIU Yu-ming,YUAN Zhi-yong,MARKHAM P N,et al.Application of power system frequency for digital audio authentication[J].IEEE Transactions on Power Delivery,2012,27(4):1820-1828.
[3] MALIK H,FARID H.Audio forensics from acoustic reverberation[C]// IEEE International Conference on Acoustics, Speech, and Signal Processing.Dallas:IEEE Press,2010:1710-1713.
[4] IKRAM S,MALIK H.Digital audio forensics using background noise[C]//IEEE International Conference on Multimedia and Expo.Singapore:IEEE Press,2010:106-110.
[5] QIAN Shi,MA Xiao-hong.Detection of audio interpolation based on singular value decomposition[C]//Awareness Science and Technology.Dalian:[s.n.],2011:287-290.
[6] YANG Rui,QU Zhen-hua,HUANG Ji-wu.Exposing MP3 audio forgeries using frame offsets[J].ACM Transactions on Multimedia Computing, Communications, and Applications,2012,33(8):1-20.
[7] CHEN Jiao-rong,XIANG Shi-jun.Exposing digital audio forgeries in time domain by using singularity analysis with wavelets[C]//Proceedings of the First ACM Workshop on Information Hiding and Multimedia Security.New York:[s.n.],2013:149-158.

备注/Memo

备注/Memo:
收稿日期: 2013-12-19
通信作者: 林晓丹(1983-),女,讲师,博士研究生,主要从事多媒体信号处理及信息安全的研究.E-mail:linxd@gmail.com.
基金项目: 福建省泉州市科技计划项目(2011G7)
更新日期/Last Update: 2015-01-20