Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/596839
Title: Audio Postprocessing Detection Based on Amplitude Cooccurrence Vector Feature
Authors: Da Luo;Mengmeng Sun;Jiwu Huang
subject: amplitude co-occurrences|digital forensics|post-processing|audio software
Year: 2016
Publisher: IEEE
Abstract: Authentication of audio signals is an important problem in multimedia forensics. Tampering is typically followed by postprocessing that aims to remove the traces of the forgery. The variety of possible postprocessing operations makes tampering detection even more challenging. In this letter, we propose the amplitude cooccurrence vector features, which exploit cooccurrence patterns in audio signals. Experimental results show that our proposed features are able to distinguish between the original audio and the postprocessed audio with an average accuracy of above 95%. Furthermore, it can also effectively discriminate different kinds of postprocessing operations.
URI: http://localhost/handle/Hannan/177105
http://localhost/handle/Hannan/596839
ISSN: 1070-9908
1558-2361
volume: 23
issue: 5
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7445827.pdf1.1 MBAdobe PDFThumbnail
Preview File
Title: Audio Postprocessing Detection Based on Amplitude Cooccurrence Vector Feature
Authors: Da Luo;Mengmeng Sun;Jiwu Huang
subject: amplitude co-occurrences|digital forensics|post-processing|audio software
Year: 2016
Publisher: IEEE
Abstract: Authentication of audio signals is an important problem in multimedia forensics. Tampering is typically followed by postprocessing that aims to remove the traces of the forgery. The variety of possible postprocessing operations makes tampering detection even more challenging. In this letter, we propose the amplitude cooccurrence vector features, which exploit cooccurrence patterns in audio signals. Experimental results show that our proposed features are able to distinguish between the original audio and the postprocessed audio with an average accuracy of above 95%. Furthermore, it can also effectively discriminate different kinds of postprocessing operations.
URI: http://localhost/handle/Hannan/177105
http://localhost/handle/Hannan/596839
ISSN: 1070-9908
1558-2361
volume: 23
issue: 5
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7445827.pdf1.1 MBAdobe PDFThumbnail
Preview File
Title: Audio Postprocessing Detection Based on Amplitude Cooccurrence Vector Feature
Authors: Da Luo;Mengmeng Sun;Jiwu Huang
subject: amplitude co-occurrences|digital forensics|post-processing|audio software
Year: 2016
Publisher: IEEE
Abstract: Authentication of audio signals is an important problem in multimedia forensics. Tampering is typically followed by postprocessing that aims to remove the traces of the forgery. The variety of possible postprocessing operations makes tampering detection even more challenging. In this letter, we propose the amplitude cooccurrence vector features, which exploit cooccurrence patterns in audio signals. Experimental results show that our proposed features are able to distinguish between the original audio and the postprocessed audio with an average accuracy of above 95%. Furthermore, it can also effectively discriminate different kinds of postprocessing operations.
URI: http://localhost/handle/Hannan/177105
http://localhost/handle/Hannan/596839
ISSN: 1070-9908
1558-2361
volume: 23
issue: 5
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7445827.pdf1.1 MBAdobe PDFThumbnail
Preview File