Source cell-phone identification from recorded speech using non-speech segments

Anshan PEI; Rangding WANG; Diqun YAN

doi:10.11959/j.issn.1000-0801.2017123

您当前的位置：

首页 >

文章列表页 >

Source cell-phone identification from recorded speech using non-speech segments

research and development | 更新时间：2024-06-05

- Source cell-phone identification from recorded speech using non-speech segments
- Telecommunications Science Vol. 33, Issue 7, Pages: 103-111(2017)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2017123
  CLC： TP391
- Published Online：2017-07，
  
  Published：20 July 2017
- 稿件说明：
移动端阅览
Anshan PEI, Rangding WANG, Diqun YAN. Source cell-phone identification from recorded speech using non-speech segments[J]. Telecommunications science, 2017, 33(7): 103-111.
DOI：

Anshan PEI, Rangding WANG, Diqun YAN. Source cell-phone identification from recorded speech using non-speech segments[J]. Telecommunications science, 2017, 33(7): 103-111. DOI： 10.11959/j.issn.1000-0801.2017123.

摘要

手机来源识别已成为多媒体取证领域重要的热点问题。提出了一种基于语音静音段特征的手机来源识别方法，该方法先通过使用自适应端点检测算法得到语音的静音段；然后将静音段的梅尔频谱系数（MFC）的均值作为分类特征；最后结合 WEKA 平台的CfsSubsetEval评价函数按照最佳优先（BestFirst）搜索进行特征选择，并采用支持向量机（SVM）对手机来源进行识别。实验部分对23款主流型号的手机进行了分类，结果表明所提特征具有较好的分类性能，在TIMIT数据库和自建的CKC-SD数据库上，平均识别准确率分别为99.23%和99.00%。另外，与语音段MFC特征和梅尔倒谱系数（MFCC）特征进行了对比，实验结果证明所提特征具有更加优越的性能。

Abstract

Source cell-phone identification has become a hot topic in multimedia forensics.A novel cell-phone identification method was proposed based on the silent segments of recorded speech.Firstly

the silent segments were obtained using adaptive endpoint detection algorithm.Then

the mean of Mel frequency coefficients (MFC) was extracted as the characteristics for device identification.Finally

the CfsSubsetEval evaluation function of WEKA platform was selected according to the best priority (BestFirst) search

and support vector machine (SVM) was used for classification.Twenty-three popular models of the cell-phones were evaluated in the experiment.Experimental results show that the proposed method is feasible and the average recognition rates are 99.23% and 99.00% on the TIMIT database and the CKC-SD database.At the same time

the proposed feature performs was demonstrated better than the MFC features and the Mel frequency cepstrum coefficients (MFCC) features of the speech segments.

关键词

Keywords

references

卢卫 , 陆希玉 . 4G时代移动互联网的发展趋势 [J ] . 电信科学 , 2014 , 30 ( 5 ): 51 - 54 .

LU W , LU X Y . Mobile internet trends in 4G era [J ] . Telecom-munications Science , 2014 , 30 ( 5 ): 51 - 54 .

卿斯汉 . Android安全的研究现状与展望 [J ] . 电信科学 , 2016 , 32 ( 10 ): 2 - 6 .

QING S H . Research status and outlook of android security [J ] . Telecommunications Science , 2016 , 32 ( 10 ): 2 - 6 .

杨锐 , 骆伟祺 , 黄继武 . 多媒体取证 [J ] . 中国科学:信息科学 , 2013 , 43 ( 12 ): 1654 - 1672 .

YANG R , LUO W Q , HUANG J W . Multimedia forensics [J ] . Science China :Information Science , 2013 , 43 ( 12 ): 1654 - 1672 .

胡永健 , 简超 , 俞兵华 . 利用彩色图像信息的源相机辨识策略 [J ] . 计算机应用 , 2010 , 30 ( 10 ): 2694 - 2697 .

HU Y J , JIAN C , YU B H . Source camera identification schemes with color image information [J ] . Journal of Computer Applications , 2010 , 30 ( 10 ): 2694 - 2697 .

周翠娟 , 周治平 . 基于模式噪声大分量的手机相机来源检测 [J ] . 计算机工程 , 2013 , 39 ( 3 ): 306 - 310 .

ZHOU C J , ZHOU Z P . Mobile phone camera origin detection based on large components of pattern noise [J ] . Computer Engi-neering , 2013 , 39 ( 3 ): 306 - 310 .

王波 , 杨福龙 . 数字图像来源取证现状与趋势 [J ] . 信息安全研究 , 2016 , 6 ( 2 ): 501 - 511 .

WANG B , YANG F L . An overview and trends on digital image source forensics [J ] . Journal of Information Security Research , 2016 , 6 ( 2 ): 501 - 511 .

GARCIA R D , ESPY W C . Automatic acquisition device identification from speech recordings [C ] // 2010 IEEE International Conference on Acoustics,Speech and Signal Processing,March 15-19,2010,Dallas,TX,USA . New Jersey:IEEE Press , 2010 : 1806 - 1809 .

MALIK H , ZHAO H . Recording environment identification using acoustic reverberation [C ] // 2012 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP),March 25-30,2012,Kyoto,Japan . New Jersey:IEEE Press , 2012 : 1833 - 1836 .

GUPTA S , CHO S , KUO C , et al . Current developments and future trends in audio authentication [J ] . IEEE Multimedia , 2012 , 19 ( 1 ): 50 - 59 .

MALIK H , MILLER J . Microphone identification using higher-order statistics [C ] // 46th International Conference:Audio Forensics,June 1,2012,Denver,CO,USA . > .[S.l.:s.n ] , 2012 : 2 - 5 .

贺前华 , 王志锋 , 朱铮宇 , 等 . 基于改进 PNCC 特征和两步区分性训练的录音设备识别方法 [J ] . 电子学报 , 2013 , 42 ( 1 ): 191 - 198 .

HE Q H , WANG Z F , ZHU Z Y , et al . A recording device identi-fication algorithm based on improved PNCC feature and two-step discriminative training [J ] . Acta Electronica Sinica , 2013 , 42 ( 1 ): 191 - 198 .

JAHNIRAD M , WAHAB A W A , ANUAR N B , et al . Blind source mobile device identification based on recorded call [J ] . Engineering Applications of Artificial Intelligence , 2014 ( 36 ): 320 - 331 .

HANILCI C , ERTAS F , ERTAS T , et al . Recognition of brand and models of cell-phones from recorded speech signals [J ] . IEEE Transactions on Information Forensics ＆ Security , 2012 , 7 ( 2 ): 625 - 634 .

HANILCI C , CEMAL I , ERTAS F . Optimizing acoustic features for source cell-phone recognition using speech signals [C ] // 2013 ACM Workshop on Information Hiding and MultimediaSecurity,June 17-19,2013,Montpellier,France . New York:ACM Press , 2013 : 141 - 148 .

KOTROPOULOS C L . Source phone identification using sketches of features [J ] . Biometrics IET , 2014 , 3 ( 2 ): 75 - 83 .

BUCHHOLZ R , KRAETZER C , DITTMANN J . Microphone classification using Fourier coefficients [C ] // 2009 International Workshop on Information Hiding,June 8-10,2009,Darmstadt,Germany . Heidelberg:Springer Berlin Heidelberg , 2009 : 235 - 246 .

王志锋 , 贺前华 , 李艳雄 . 录音设备的建模和识别算法 [J ] . 信号处理 , 2013 , 29 ( 4 ): 419 - 428 .

WANG Z F , HE Q H , LI Y X . A modeling and identification algorithm of recording devices [J ] . Journal of Signal Processing , 2013 , 29 ( 4 ): 419 - 428 .

KINNUNEN T , RAJAN P . A practical,self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data [C ] // 2013 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP),May 26-31,2013,Vancouver,Canada . New Jersey:IEEE Press , 2013 : 7229 - 7233 .

XU L , YAN P , CHANG T . Best first strategy for feature selection [C ] // 1988 9th International Conference on Pattern Recognition,May 14-November 17,1988,Rome,Italy . New Jersey:IEEE Press , 1988 : 706 - 708 .

HALL M A . Correlation-based feature selection for machine learning [D ] . Hamilton:The University of Waikato , 1999 .

何振红 . 基于特征加权FDCT和模糊最小二乘支持向量机的虹膜识别算法 [J ] . 电信科学 , 2016 , 32 ( 3 ): 92 - 98 .

HE Z H . Iris recognition algorithm based on feature weighting fast discrete curvelet transform and fuzzy LS-SVM [J ] . Tele-communications Science , 2016 , 32 ( 3 ): 92 - 98 .

Views

881

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰