Magdalena Fuentes, Pablo Zinemanas, Pablo Cancela, J. A. Apolinário
{"title":"Detection of ENF discontinuities using PLL for audio authenticity","authors":"Magdalena Fuentes, Pablo Zinemanas, Pablo Cancela, J. A. Apolinário","doi":"10.1109/LASCAS.2016.7451014","DOIUrl":null,"url":null,"abstract":"A Phase Locked Loop (PLL) based method for determining audio authenticity is proposed in this work. Assuming that the power grid signal is embedded in an audio signal, certain pre-processing techniques are applied in order to obtain the Electrical Network Frequency (ENF). A PLL is then used to estimate the time-varying phase of the ENF signal. Postprocessing is carried out so as to improve system performance. Finally, an automatic decision on the authenticity of the audio is conducted by quantifying the frequency variations of the VCO output. The performance of the proposed method is evaluated on digitally edited and original audio signals, with promising results (achieving an accuracy of 96%).","PeriodicalId":129875,"journal":{"name":"2016 IEEE 7th Latin American Symposium on Circuits & Systems (LASCAS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE 7th Latin American Symposium on Circuits & Systems (LASCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LASCAS.2016.7451014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
A Phase Locked Loop (PLL) based method for determining audio authenticity is proposed in this work. Assuming that the power grid signal is embedded in an audio signal, certain pre-processing techniques are applied in order to obtain the Electrical Network Frequency (ENF). A PLL is then used to estimate the time-varying phase of the ENF signal. Postprocessing is carried out so as to improve system performance. Finally, an automatic decision on the authenticity of the audio is conducted by quantifying the frequency variations of the VCO output. The performance of the proposed method is evaluated on digitally edited and original audio signals, with promising results (achieving an accuracy of 96%).