基于线性预测梅尔频率倒谱系数的设备来源识别
|
摘要
由于手机录音设备的不断普及,各种功能强大的数字媒体编辑软件的出现,鉴别手机录音设备所录制的音频数据的真伪已经成为数字取证技术关注的热点问题。本文将线性预测系数(LPC)和梅尔频率倒谱系数(MFCC)特征进行结合,得到新的特征,即线性预测梅尔频率倒谱系数(LPMFCC)。然后将LPMFCC与能量特征结合得到的组合特征作为手机的指纹,选择支持向量机LIBSVM作为分类器,在两种语音库上进行手机设备来源识别实验。实验表明,LPMFCC特征作为手机指纹进行实验的识别率相对于LPC提升了12%,相对于MFCC提升了2%,并且LPMFCC与能量特征的组合特征相比于单一的LPMFCC特征对手机录音设备的来源更有区分性。
引文
[1]HANILCI C,CEMAL I,ERTAS F.Optimizing acoustic features for source cell-phone recognition using speech signals[C].ACM Workshop on Information Hiding and Multimedia Security.Montpellier,France,2013:141-148
[2]ZOU L,YANG J C,HUANG T S.Automatic cell phone recognition from speech recordings[C].Proc.Signal and Information Processing(China SIP),2014 IEEE China Summit&International Conference on,2014:621–625
[3]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
[4]HANILCI C,KINNUNEN T.Source cell-phone recognition from recorded speech using non-speech segments[J].Digital Signal Processing,2014,35:75–85
[5]邹领,贺前华,邝细超,李洪滔,蔡梓文.基于设备噪声估计的录音设备来源识别[J].吉林大学学报,2017,47(1):274-280
[6]JIN C,WANG R D,YAN D Q,et al.Source cell-phone identification using spectral features of device self-noise[C].International Workshop on Digital Watermarking,2016:29-45
[7]KOTROPOULOS C,SAMARAS S.Mobile phone identification using recorded speech signals[C].International Conference on Digital Signal Processing,DSP,2014:586-591
[8]KOTROPOULOS C L.Source phone identification using sketches of features[J].IET Biometrics,2014,3(2):75-83
[9]PANAGAKIS Y,KOTROPOULOS C.Automatic telephone handset identification by sparse representation of random spectral features,in:Proc.14th ACM Multi-media and Security Workshop,Coventry,UK,2012,pp.91–96
[10]PANAGAKIS Y,KOTROPOULOS C.Telephone handset identification by feature selection and sparse representations[C].IEEE International Workshop on Information Forensics and Security.IEEE,2012:73-78
[11]ZOU L,HE Q H,FENG X H.Cell phone verification from speech recordings using sparse representation[C].ICASSP,EEE International Conference on Acoustics,Speech and Signal Processing-Proceedings,2015:1787-1791
[12]GAROFOLO J S,LAMEL L F,FISHER W M,et al.DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM.NIST speech disc 1-1.1[J].Nasa Sti/recon Technical Report N,1993
[13]KOCAL O H,YURUKLU E,AVCIBAS I.Chaotic type features for speech steganalysis[J].IEEE Transactions on Information Forensics&Security,2008,3(4):651-661
[14]DEHZANGI O,MA B,CHNG E S,et al.Discriminative output coding features for speech recognition[C].International Symposium on Chinese Spoken Language Processing,IEEE,2008:1-4
[15]REYNOLDS D A.Speaker identification and verification using Gaussian mixture speaker models[J].Speech Communication,1995,17(1–2):91-108
[16]CHANG C C,LIN C J.LIBSVM:A Library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3)
[17]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):625-63
[2]ZOU L,YANG J C,HUANG T S.Automatic cell phone recognition from speech recordings[C].Proc.Signal and Information Processing(China SIP),2014 IEEE China Summit&International Conference on,2014:621–625
[3]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
[4]HANILCI C,KINNUNEN T.Source cell-phone recognition from recorded speech using non-speech segments[J].Digital Signal Processing,2014,35:75–85
[5]邹领,贺前华,邝细超,李洪滔,蔡梓文.基于设备噪声估计的录音设备来源识别[J].吉林大学学报,2017,47(1):274-280
[6]JIN C,WANG R D,YAN D Q,et al.Source cell-phone identification using spectral features of device self-noise[C].International Workshop on Digital Watermarking,2016:29-45
[7]KOTROPOULOS C,SAMARAS S.Mobile phone identification using recorded speech signals[C].International Conference on Digital Signal Processing,DSP,2014:586-591
[8]KOTROPOULOS C L.Source phone identification using sketches of features[J].IET Biometrics,2014,3(2):75-83
[9]PANAGAKIS Y,KOTROPOULOS C.Automatic telephone handset identification by sparse representation of random spectral features,in:Proc.14th ACM Multi-media and Security Workshop,Coventry,UK,2012,pp.91–96
[10]PANAGAKIS Y,KOTROPOULOS C.Telephone handset identification by feature selection and sparse representations[C].IEEE International Workshop on Information Forensics and Security.IEEE,2012:73-78
[11]ZOU L,HE Q H,FENG X H.Cell phone verification from speech recordings using sparse representation[C].ICASSP,EEE International Conference on Acoustics,Speech and Signal Processing-Proceedings,2015:1787-1791
[12]GAROFOLO J S,LAMEL L F,FISHER W M,et al.DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM.NIST speech disc 1-1.1[J].Nasa Sti/recon Technical Report N,1993
[13]KOCAL O H,YURUKLU E,AVCIBAS I.Chaotic type features for speech steganalysis[J].IEEE Transactions on Information Forensics&Security,2008,3(4):651-661
[14]DEHZANGI O,MA B,CHNG E S,et al.Discriminative output coding features for speech recognition[C].International Symposium on Chinese Spoken Language Processing,IEEE,2008:1-4
[15]REYNOLDS D A.Speaker identification and verification using Gaussian mixture speaker models[J].Speech Communication,1995,17(1–2):91-108
[16]CHANG C C,LIN C J.LIBSVM:A Library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3)
[17]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):625-63