期刊文献+

基于Duffing共振的语音真伪检测技术研究

Detection of speech authenticity based on duffing resonance
下载PDF
导出
摘要 在数字语音真伪技术中,基于电网频率的检测方法是当前研究的热点。由于数字录音设备在录音过程中不仅记录语音内容本身,还携带微弱的电网电压或电流信号,利用Duffing共振理论来提取数字录音信号中的微弱电网信号,根据其输出特征参数的幅频特性和相频特性来判断录音文件的真伪性。通过实验分析论证了该方法的可行性和实用性,为数字录音真伪鉴别技术提供了一条新的研究方向。 At present,in the group of digital speech authenticity technology,the detection method based on eleetrie network frequency is a hotspot.The digital recording equipment which not only records the voice signal in recording process,but also records weak voltage or current signal.Because of this reason,The theory of Duffing resonance is used to extract the weak eleetrie network frequency in digital speech signal.According to its amplitude-frequency characteristic and phase-frequency characteristic of output characteristic parameters,the authenticity of the recording file has been judged.Based on experimental analysis,the feasibility and practicability of the method is improved,thus,it provides an efficient path for digital recording authenticity technology.
作者 何朝霞 刘凯
出处 《微型机与应用》 2016年第2期35-38,共4页 Microcomputer & Its Applications
基金 长江大学工程技术学院科学研究发展基金(15j0401)
关键词 语音真伪鉴别 电网频率 Duffing共振 特征参数 detection of speech authenticity eleetrie network frequency Duffing resonance characteristic parameters
  • 相关文献

参考文献8

  • 1GUPTA S,CHO S,JAYKUO C C.Current developments and future trends in audio authentication[J].IEEE Multimedia,2012,19(1):50-59.
  • 2GRIGORAS C.Digital audio recording analysis:The electric network frequency criterion[C].Diamond Cut Productions,Inc.,Applications Notes AN-4,2003.
  • 3GRIGORAS C.Digital audio recording analysis:the electric network frequency(ENF)criterion[J].The International Journal of Speech Language and the Law,2005,12(1):63-76.
  • 4GRIGORAS C.Applications of ENF criterion in forensic audio,video,computer and telecommunication analysis[J].Forensic Science International,2007(167):136-143.
  • 5GRIGORAS C.Applications of ENF analysis in forensic authentication of digital audio and video recordings[J].The Journal of Audio Engineering Society,2009,57(9):643-661.
  • 6杨林国.词类扩充方法在语音识别中的应用[J].电子技术应用,2014,40(6):123-125. 被引量:3
  • 7赵媛媛,王力.基于流形学习ISOP算法的语音特征提取及应用研究[J].微型机与应用,2014,33(1):43-45. 被引量:1
  • 8赖志慧,冷永刚,孙建桥,范胜波.基于Duffing振子的变尺度微弱特征信号检测方法研究[J].物理学报,2012,61(5):60-68. 被引量:79

二级参考文献26

  • 1戴海生,朱小燕,罗予频,杨士元.实用的家电语音控制系统的设计[J].电子技术应用,2005,31(9):43-45. 被引量:2
  • 2张广军,徐健学,姚宏.含噪双稳杜芬振子矩方程的分岔与随机共振[J].力学学报,2006,38(2):283-288. 被引量:5
  • 3衣文索,石要武,聂春燕.混沌态杜芬振子与弱正弦信号参量估计[J].计量学报,2006,27(2):156-159. 被引量:14
  • 4周凯波,豆成权,陈涛.两种微弱正弦信号检测方法比较研究[J].武汉理工大学学报(信息与管理工程版),2007,29(4):53-55. 被引量:4
  • 5FEDERICO M. Efficient language model adaptation through MDI estimation[C]. Eurospeeeh, 1999:1583-1586.
  • 6ROSENFELD R. A maximum ent- ropy approach to adaptive statistical language modelling[J].Computer Spe- ech & Language, 1996,10(3):187- 228.
  • 7JELINEK F, MERCER R L. Inter- polated estimation of Markov source parameters from sparse data[C].Pattern recognition in prac- tice, 1980:381 - 397.
  • 8SLAVA K. Estimation of probabilities from sparse data for the language model component of a speech recognizer[J]. Acoustics, Speech and Signal Processing, IEEE Transac- tions on, 1987,35 (3) : 400- 401.
  • 9MEHRYAR M, PEREIRA F, RILEY M. Weighted finite- state transducers in speech recognition[J]. Computer Speech & Language, 2002,16 ( 1 ) : 69- 88.
  • 10DARREN M, DINES J, DOSS M M, et al. Juicer: A weighted finite-state transducer speech decoder[C].Machine Learning for Multimodal Interaction, Springer Berlin Hei- delberg, 2006:285-296.

共引文献80

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部