Copy-move detection of audio recording with pitch similarity

The widespread availability of audio editing software has made it very easy to create forgeries without perceptual trace. Copy-move is one of popular audio forgeries. It is very important to identify audio recording with duplicated segments. However, copy-move detection in digital audio with sample...

Full description

Saved in:
Bibliographic Details
Published in2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1782 - 1786
Main Authors Qi Yan, Rui Yang, Jiwu Huang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2015
Subjects
Audio databases
Audio forensics
Audio forgeries
Copy-Move detection
Fingerprint recognition
Forgery
Image segmentation
Pitch similarity
Robustness
Security
Online AccessGet full text

Cover

More Information
Summary:The widespread availability of audio editing software has made it very easy to create forgeries without perceptual trace. Copy-move is one of popular audio forgeries. It is very important to identify audio recording with duplicated segments. However, copy-move detection in digital audio with sample by sample comparison is invalid due to post-processing after forgeries. In this paper we present a method based on pitch similarity to detect copy-move forgeries. We use a robust pitch tracking method to extract the pitch of every syllable and calculate the similarities of these pitch sequences. Then we can use the similarities to detect copy-move forgeries of digital audio recording. Experimental result shows that our method is feasible and efficient.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2015.7178277