针对多种处理痕迹的数字语音取证算法

doi:10.11772/j.issn.1001-9081.2018071596

计算机应用 ›› 2019, Vol. 39 ›› Issue (1): 126-130.DOI: 10.11772/j.issn.1001-9081.2018071596

• 2018年全国开放式分布与并行计算学术年会(DPCS 2018)论文 • 上一篇下一篇

针对多种处理痕迹的数字语音取证算法

向立, 严迪群, 王让定, 李孝文

宁波大学信息科学与工程学院, 浙江宁波 315211

收稿日期:2018-07-19 修回日期:2018-08-07 出版日期:2019-01-10 发布日期:2019-01-21
通讯作者: 严迪群
作者简介:向立(1994-),男,湖南湘西人,硕士研究生,主要研究方向:多媒体通信、信息安全;严迪群(1979-),男,浙江余姚人,副教授,博士,CCF会员,主要研究方向:多媒体通信、信息安全;王让定(1962-),男,甘肃天水人,教授,博士,CCF会员,主要研究方向:多媒体通信安全、信息隐藏与隐写分析;李孝文(1996-),男,浙江温州人,硕士研究生,主要研究方向:多媒体通信、信息安全。
基金资助:
国家自然科学基金资助项目（U1736215，61672302）；浙江省自然科学基金资助项目（LZ15F020002，LY17F020010）；宁波市自然科学基金资助项目（2017A610123）；宁波大学学科基金资助项目（XKXL1509，XKXL1503）。

Forensics algorithm of various operations for digital speech

XIANG Li, YAN Diqun, WANG Rangding, LI Xiaowen

Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo Zhejiang 315211, China

Received:2018-07-19 Revised:2018-08-07 Online:2019-01-10 Published:2019-01-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (U1736215, 61672302), the Natural Science Foundation of Zhejiang Province (LZ15F020002, LY17F020010), the Natural Science Foundation of Ningbo (2017A610123), the Ningbo University Fund (XKXL1509, XKXL1503).

摘要/Abstract

摘要： 现有的数字语音取证研究主要集中于对单一的某种操作进行检测，无法对不相关的操作进行判断。针对该问题，提出了一种能够同时检测经过变调、低通滤波、高通滤波和加噪这四种操作的数字语音取证方法。首先，计算语音的归一化梅尔频率倒谱系数（MFCC）统计矩特征；然后通过多个二分类器对特征进行训练，并组合投票得到多分类器；最后使用该多分类器对待测语音进行分类。在TIMIT以及UME语音库上的实验结果表明，归一化MFCC统计矩特征在库内实验中均达到了97%以上的检测率，且在对MP3压缩鲁棒性测试的实验中，检测率仍能保持在96%以上。

关键词: 语音取证, 梅尔频率倒谱系数, 处理痕迹, 多分类器

Abstract: Most existing forensic methods for digital speech aim at detecting a specific operation, which means that these methods can not identify various operations at a time. To solve the problem, a universal forensic algorithm for simultaneously detecting various operations, such as pitch modification, low-pass filtering, high-pass filtering, and noise adding was proposed. Firstly, the statistical moments of Mel-Frequency Cepstral Coefficients (MFCC) were calculated, and cepstrum mean and variance normalization were applied to the moments. Then, a multi-class classifier based on multiple two-class classifiers was constructed. Finally, the classifier was used to identify various types of speech operations. The experimental results on TIMIT and UME speech datasets show that the proposed universal features achieve detection accuracy over 97% for various speech operations. And the detection accuracy in the test of MP3 compression robustness is still above 96%.

Key words: speech forensics, Mel-Frequency Cepstral Coefficient (MFCC), operation trace, multi-class classifier

中图分类号:

向立, 严迪群, 王让定, 李孝文. 针对多种处理痕迹的数字语音取证算法[J]. 计算机应用, 2019, 39(1): 126-130.

XIANG Li, YAN Diqun, WANG Rangding, LI Xiaowen. Forensics algorithm of various operations for digital speech[J]. Journal of Computer Applications, 2019, 39(1): 126-130.

参考文献

[1] LUO D, YANG R, LI B, et al. Detection of double compressed AMR audio using stacked autoencoder[J]. IEEE Transactions on Information Forensics and Security, 2017, 12(2):432-444.
[2] LUO D, YANG R, HUANG J W. Detecting double compressed AMR audio using deep learning[C]//ICASSP 2014:Proceedings of the 39th International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2014:2669-2673.
[3] WU H J, WANG Y, HUANG J W. Identification of electronic disguised voices[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(3):489-500.
[4] WU H, WANG Y, HUANG J W. Blind detection of electronic disguised voice[C]//ICASSP 2013:Proceedings of the 38th International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2013:3013-3017.
[5] 徐宏伟,严迪群,阳帆,等.基于卷积神经网络的电子变调语音检测算法[J].电信科学,2018,34(2):46-57.(XU H W, YAN D Q, YANG F, et al. Detection algorithm of electronic disguised voice based on convolutional neural network[J]. Telecommunications Science, 2018, 34(2):46-57.)
[6] LUO D, KORUS P, HUANG J W. Band energy difference for source attribution in audio forensics[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(9):2179-2189.
[7] ZOU L, HE Q H, FENG X H. Cell phone verification from speech recordings using sparse representation[C]//ICASSP 2015:Proceedings of the 40th International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2015:1787-1791.
[8] QI S M, HUANG Z, LI Y, et al. Audio recording device identification based on deep learning[C]//ICSIP 2016:Proceedings of the 2016 International Conference on Signal and Image Processing. Piscataway, NJ:IEEE, 2016:426-431.
[9] JAKUB G, MARCIN G, RAFAL S. Playback attack detection for text-dependent speaker verification over telephone channels[J]. Speech Communication, 2015, 67:143-153.
[10] LI H D, LUO W Q, QIU X Q, et al. Identification of various image operations using residual-based features[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(1):31-45.
[11] PRASAD N V, UMESH S. Improved cepstral mean and variance normalization using Bayesian framework[C]//ASRU 2013:Proceedings of the 2013 Automatic Speech Recognition and Understanding. Piscataway, NJ:IEEE, 2014:156-161.
[12] KNERR S, PERSONNAZ L, DREYFUS G. Single-layer learning revisited:a stepwise procedure for building and training a neural network[J]. Neurocomputing:Algorithms, Architectures and Application, 1990, 68(11):41-50.

针对多种处理痕迹的数字语音取证算法

Forensics algorithm of various operations for digital speech

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

[1]	郇战, 陈学杰, 吕士云, 耿宏杨. 基于多分类器融合的步态识别方法[J]. 计算机应用, 2019, 39(3): 712-718.
[2]	王天锐, 鲍骞月, 秦品乐. 基于梅尔倒谱系数、深层卷积和Bagging的环境音分类方法[J]. 计算机应用, 2019, 39(12): 3515-3521.
[3]	阳帆, 严迪群, 徐宏伟, 王让定, 金超, 向立. 基于噪声一致性的数字语音异源拼接篡改检测算法[J]. 计算机应用, 2017, 37(12): 3452-3457.
[4]	谢小娟, 曾以成, 熊冰峰. 说话人识别中基于Fisher比的特征组合方法[J]. 计算机应用, 2016, 36(5): 1421-1425.
[5]	阮锦佳, 罗丹, 罗海勇. 基于支持向量机多分类器的室内外场景感知算法[J]. 计算机应用, 2015, 35(11): 3135-3138.
[6]	张亮陈睿邱小松. 谱聚类递归神经网络集成的全自动公开区分计算机和人的图灵测试识别算法[J]. 计算机应用, 2014, 34(5): 1383-1385.
[7]	张小霞李应. 基于能量检测的复杂环境下的鸟鸣识别[J]. 计算机应用, 2013, 33(10): 2945-2949.
[8]	胡峰松张璇. 基于梅尔频率倒谱系数与翻转梅尔频率倒谱系数的说话人识别方法[J]. 计算机应用, 2012, 32(09): 2542-2544.
[9]	胡步发陈炳兴黄银成. 基于表情子空间多分类器集成的非特定人人脸表情识别[J]. 计算机应用, 2011, 31(03): 736-740.