ESPRIT-Hilbert-based audio tampering detection with SVM classifier for forensic analysis via electrical network frequency

Reis, Paulo Max Gil Innocencio; Costa, João Paulo Carvalho Lustosa da; Miranda, Ricardo Kehrle; Del Galdo, Giovanni

Registro completo de metadados

Campo DC	Valor	Idioma
dc.contributor.author	Reis, Paulo Max Gil Innocencio	-
dc.contributor.author	Costa, João Paulo Carvalho Lustosa da	-
dc.contributor.author	Miranda, Ricardo Kehrle	-
dc.contributor.author	Del Galdo, Giovanni	-
dc.date.accessioned	2025-02-04T11:19:38Z	-
dc.date.available	2025-02-04T11:19:38Z	-
dc.date.issued	2017	-
dc.identifier.citation	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.	pt_BR
dc.identifier.uri	http://repositorio.unb.br/handle/10482/51453	-
dc.language.iso	eng	pt_BR
dc.publisher	IEEE	pt_BR
dc.rights	Acesso Restrito	pt_BR
dc.title	ESPRIT-Hilbert-based audio tampering detection with SVM classifier for forensic analysis via electrical network frequency	pt_BR
dc.type	Artigo	pt_BR
dc.subject.keyword	Processamento de sinais acústicos	pt_BR
dc.subject.keyword	Gravações de áudio	pt_BR
dc.subject.keyword	Análise forense	pt_BR
dc.subject.keyword	Áudio - adulteração	pt_BR
dc.subject.keyword	Frequência da rede elétrica	pt_BR
dc.identifier.doi	10.1109/TIFS.2016.2636095	pt_BR
dc.relation.publisherversion	https://ieeexplore.ieee.org/document/7775065	pt_BR
dc.description.abstract1	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.	pt_BR
dc.contributor.affiliation	University of Brasília, Department of Electrical Engineering	pt_BR
dc.contributor.affiliation	National Institute of Criminalistics, Forensic Examination Service of Electronic and Multimedia Evidences, Brasília, DF, Brazil	pt_BR
dc.contributor.affiliation	University of Brasília, Department of Electrical Engineering	pt_BR
dc.contributor.affiliation	Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany	pt_BR
dc.contributor.affiliation	lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany	pt_BR
dc.contributor.affiliation	University of Brasília, Department of Electrical Engineering	pt_BR
dc.contributor.affiliation	lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany	pt_BR
dc.contributor.affiliation	Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany	pt_BR
dc.contributor.affiliation	lmenau University of Technology, Institute for Information Technology, Ilmenau, Germany	pt_BR
dc.description.unidade	Faculdade de Tecnologia (FT)	pt_BR
dc.description.unidade	Departamento de Engenharia Elétrica (FT ENE)	pt_BR
dc.description.ppg	Programa de Pós-Graduação em Engenharia Elétrica	pt_BR
Aparece nas coleções:	Artigos publicados em periódicos e afins