...
首页> 外文期刊>Computer Science & Information Technology >A Novel ENF Extraction Approach for Region-of-Recording Identification of Media Recordings
【24h】

A Novel ENF Extraction Approach for Region-of-Recording Identification of Media Recordings

机译:一种新的ENF提取方法,用于媒体记录的记录区域识别

获取原文
           

摘要

The electric network frequency (ENF) of power lines leaves its trace in nearby mediarecordings. The ENF signals vary in a consistent way in a given power grid. Therefore, it ispossible to develop signal processing and machine learning techniques to identify the grid oforigin by extracting attributes of the embedded ENF signal in recorded audio. This paperpresents a model based on a novel ENF extraction technique with training on audio and powerrecordings from different grids. The proposed approach is based on correcting erroneouslyselected peaks from the Short Time Fourier Transform (STFT) by leveraging time correlations.These peaks are mistakenly taken for the frequency component belonging to the embedded ENFsignal of the power grid and are corrected by the algorithm. Results on a test set of 50recordings from nine different locations demonstrate the effectiveness of the proposed approachwith an overall accuracy of 88%.
机译:电力线的电网频率(ENF)在附近的媒体记录中留下痕迹。在给定的电网中,ENF信号以一致的方式变化。因此,有可能发展信号处理和机器学习技术以通过提取记录的音频中嵌入的ENF信号的属性来识别起源网格。本文提出了一种基于新型ENF提取技术的模型,该模型对来自不同网格的音频和功率记录进行了训练。提出的方法是基于利用时间相关性校正从短时傅立叶变换(STFT)中错误选择的峰值的,这些峰值被误认为属于电网嵌入式ENF信号的频率分量,并通过算法进行了校正。在来自9个不同位置的50个记录的测试集上的结果证明了该方法的有效性,总体准确性为88%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号