基于卷积神经网络的翻录语音检测算法

doi:10.11772/j.issn.1001-9081.2017071896

计算机应用 ›› 2018, Vol. 38 ›› Issue (1): 79-83.DOI: 10.11772/j.issn.1001-9081.2017071896

• 2017年全国开放式分布与并行计算学术年会(DPCS 2017)论文 • 上一篇下一篇

基于卷积神经网络的翻录语音检测算法

李璨, 王让定, 严迪群

宁波大学信息科学与工程学院, 浙江宁波 315211

收稿日期:2017-08-01 修回日期:2017-08-19 出版日期:2018-01-10 发布日期:2018-01-22
通讯作者: 王让定
作者简介:李璨(1992-),女,安徽淮北人,硕士研究生,主要研究方向:多媒体信息安全;王让定(1962-),男,浙江宁波人,教授,博士,CCF会员,主要研究方向:多媒体信息安全、数字取证;严迪群(1979-),男,浙江宁波人,副教授,博士,CCF会员,主要研究方向:多媒体信息安全、数字取证。
基金资助:
国家自然科学基金资助项目（61672302，61300055）；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）；宁波大学科研基金资助项目（XKXL1509，XKXL1503）；宁波大学王宽诚幸福基金资助项目。

Recaptured speech detection algorithm based on convolutional neural network

LI Can, WANG Rangding, YAN Diqun

College of Information Science and Engineering, Ningbo University, Ningbo Zhejiang 315211, China

Received:2017-08-01 Revised:2017-08-19 Online:2018-01-10 Published:2018-01-22
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61672302, 61300055), the Natural Science Foundation of Zhejiang Province (LZ15F020002, LY17F020010), the Natural Science Foundation of Ningbo (2017A610123),the Scientific Research Foundation of Ningbo University (XKXL1509, XKXL1503),the K.C. Wong Magna Fund in Ningbo University.

摘要/Abstract

摘要： 针对翻录语音攻击说话人识别系统，危害合法用户的权益问题，提出了一种基于卷积神经网络（CNN）的翻录语音检测算法。首先，通过提取原始语音与翻录语音的语谱图，并将其输入到卷积神经网络中，对其进行特征提取及分类；然后，搭建了适应于检测翻录语音的网络框架，分析讨论了输入不同窗移的语谱图对检测率的影响；最后，对不同偷录及回放设备的翻录语音进行了交叉实验检测，并与现有的经典算法进行了对比。实验结果表明，所提方法能够准确地判断待测语音是否为翻录语音，其识别率达到了99.26%，与静音段梅尔频率倒谱系数（MFCC）算法、信道模式噪声算法和长时窗比例因子算法相比，识别率分别提高了约26个百分点、21个百分点和0.35个百分点。

关键词: 卷积神经网络, 翻录语音检测, 语谱图, 录音设备, 网络框架

Abstract: Aiming at the problems that recaptured speech attack to speaker recognition system harms the rights and interests of legitimate users, a recaptured speech detection algorithm based on Convolutional Neural Network (CNN) was proposed. Firstly, the spectrograms of the original speech and the recaptured speech were extracted and input into the CNN for feature extraction and classification. Secondly, for the detection task, a new network architecture was constructed, and the effect of the spectrograms with different window shifts were discussed. Finally, the cross-over experiments for various recapture and replay devices were constructed. The experimental results demonstrate that the proposed method can accurately discriminate whether the detected speech is recaptured or not, and the recognition rate achieves 99.26%. Compared with the mute segment Mel-Frequency Cepstral Coefficient (MFCC) algorithm, channel mode noise algorithm and long window scale factor algorithm, the recognition rate is increased by about 26 percentage points, about 21 percentage points and about 0.35 percentage points respectively.

Key words: Convolutional Neural Network (CNN), recaptured speech detection, spectrogram, recording device, network architecture

中图分类号:

李璨, 王让定, 严迪群. 基于卷积神经网络的翻录语音检测算法[J]. 计算机应用, 2018, 38(1): 79-83.

LI Can, WANG Rangding, YAN Diqun. Recaptured speech detection algorithm based on convolutional neural network[J]. Journal of Computer Applications, 2018, 38(1): 79-83.

参考文献

[1] SHANG W, STEVENSON M. A playback attack detector for speaker verification systems[C]//Proceedings of the 2008 International Symposium on Communications, Control and Signal Processing. Piscataway, NJ:IEEE, 2008:1144-1149.
[2] SHANG W, STEVENSON M. Score normalization in playback attack detection[C]//Proceedings of the 2010 IEEE International Conference on Acoustics Speech and Signal Processing 2010. Piscataway, NJ:IEEE, 2010:1678-1681.
[3] JAKUB G, MARCIN G, RAFAL S. Playback attack detection for text-dependent speaker verification over telephone channels[J]. Speech Communication, 2015, 67:143-153.
[4] WU Z, GAO S, CLING E S, et al. A study on replay attack and anti-spoofing for text-dependent speaker verification[C]//Proceedings of the 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Piscataway, NJ:IEEE, 2015:35-45.
[5] 张利鹏,曹犟,徐明星.防止假冒者闯入说话人识别系统[J].清华大学学报(自然科学版),2008,48(S1):699-703.(ZHANG L P, CAO J, XU M X. Prevention of impostors entering speaker recognition systems[J]. Journal of Tsinghua University (Science and Technology), 2008, 48(S1):699-703.)
[6] 王志锋,贺前华,张雪源,等.基于信道模式噪声的录音回放攻击检测[J].华南理工大学学报(自然科学版),2011,39(10):7-12.(WANG Z F, HE Q H, ZHANG X Y, et al. Channel pattern noise based playback detection algorithm speaker recognition[J]. Journal of South China University of Technology (Natural Science Edition), 2011, 39(10):7-12.)
[7] WANG Z F, WEI G, HE Q H. Channel pattern noise based playback attack detection algorithm for speaker recognition[C]//Processing of the 2011 International Conference on Machine Learning and Cybernetics. Piscataway, NJ:IEEE, 2011:1708-1713.
[8] VILLABA J, LLEIDA E. Detecting replay attacks from far-field recordings on speaker verification systems[C]//BioID 2011:Proceedings of the 2011 European Workshop on Biometrics and Identity Management. Berlin:Springer, 2011:274-285.
[9] VILLABA J, LLEIDA E. Preventing replay attacks on speaker verification systems[C]//Processing of the 2011 IEEE International Carnahan Conference on Security Technology. Piscataway, NJ:IEEE, 2011:1-8.
[10] CHEN Y N, WANG R D, YAN D Q, et al. Voice playback detection based on long-window scale-factors[J]. International Journal of Security and Its Application, 2016, 10(12):299-310.
[11] LIN X, LIU J, KANG X. Audio recapture detection with convolutional neural networks[J]. IEEE Transactions on Multimedia, 2016, 18(8):1480-1487.
[12] 王天庆,李爱军.连续汉语语音识别语料库的设计[C]//第六届全国现代语音学学术会议.天津:天津大学出版社2004:544-547.(WANG T Q, LI A J. The design of the continuous Chinese speech recognition corpus[C]//Proceedings of the Sixth National Conference on Modern Phonetics Learning. Tianjin:Tianjin University Press, 2004:544-547.)

[1]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[2]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[8]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[9]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[10]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[11]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[12]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[13]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[14]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.
[15]	杨粟, 欧阳智, 杜逆索. 基于相关度距离的无监督并行哈希图像检索[J]. 计算机应用, 2021, 41(7): 1902-1907.

基于卷积神经网络的翻录语音检测算法

Recaptured speech detection algorithm based on convolutional neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics