Título:	ESPRIT-Hilbert-based audio tampering detection with SVM classifier for forensic analysis via electrical network frequency
Autor(es):	Reis, Paulo Max Gil Innocencio Costa, João Paulo Carvalho Lustosa da Miranda, Ricardo Kehrle Del Galdo, Giovanni
Afiliação do autor:	University of Brasília, Department of Electrical Engineering National Institute of Criminalistics, Forensic Examination Service of Electronic and Multimedia Evidences, Brasília, DF, Brazil University of Brasília, Department of Electrical Engineering Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany University of Brasília, Department of Electrical Engineering lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany
Assunto:	Processamento de sinais acústicos Gravações de áudio Análise forense Áudio - adulteração Frequência da rede elétrica
Data de publicação:	2017
Editora:	IEEE
Referência:	REIS, Paulo Max Gil Innocencio et al. ESPRIT-Hilbert-based audio tampering detection with SVM classifier for forensic analysis via electrical network frequency. IEEE Transactions on Information Forensics and Security, [S. l.], v. 12, n. 4, p. 853-864, apr. 2017. DOI: 10.1109/TIFS.2016.2636095.
Abstract:	Audio authentication is a critical task in multimedia forensics demanding robust methods to detect and identify tampered audio recordings. In this paper, a new technique to detect adulterations in audio recordings is proposed by exploiting abnormal variations in the electrical network frequency (ENF) signal eventually embedded in a questioned audio recording. These abnormal variations are caused by abrupt phase discontinuities due to insertions and suppressions of audio snippets during the tampering task. First, we propose an ESPRIT-Hilbert ENF estimator in conjunction with an outlier detector based on the sample kurtosis of the estimated ENF. Next, we use the computed kurtosis as an input for a support vector machine classifier to indicate the presence of tampering. The proposed scheme, herein designated as SPHINS, significantly outperforms related previous tampering detection approaches in the conducted tests. We validate our results using the Carioca 1 corpus with 100 unedited authorized audio recordings of phone calls.
Unidade Acadêmica:	Faculdade de Tecnologia (FT) Departamento de Engenharia Elétrica (FT ENE)
Programa de pós-graduação:	Programa de Pós-Graduação em Engenharia Elétrica
DOI:	10.1109/TIFS.2016.2636095
Versão da editora:	https://ieeexplore.ieee.org/document/7775065
Aparece nas coleções:	Artigos publicados em periódicos e afins

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.