上海交通大学学报(英文版) ›› 2014, Vol. 19 ›› Issue (4): 392-397.doi: 10.1007/s12204-014-1515-5

• • 上一篇    下一篇

Audio Authenticity: Duplicated Audio Segment Detection in Waveform Audio File

XIAO Ji-nian1 (肖佶年), JIA Yun-zhe1 (贾蕴哲), FU Er-dong1 (付尔东),HUANG Zheng1* (黄征), LI Yan2 (李岩), SHI Shao-pei2 (施少培)   

  1. (1. College of Information Security, Shanghai Jiaotong University, Shanghai 200240, China; 2. Institute of Forensic Science, Ministry of Justice, Shanghai 200063, China)
  • 出版日期:2014-08-30 发布日期:2014-10-13
  • 通讯作者: HUANG Zheng(黄征) E-mail:huang-zheng@sjtu.edu.cn

Audio Authenticity: Duplicated Audio Segment Detection in Waveform Audio File

XIAO Ji-nian1 (肖佶年), JIA Yun-zhe1 (贾蕴哲), FU Er-dong1 (付尔东),HUANG Zheng1* (黄征), LI Yan2 (李岩), SHI Shao-pei2 (施少培)   

  1. (1. College of Information Security, Shanghai Jiaotong University, Shanghai 200240, China; 2. Institute of Forensic Science, Ministry of Justice, Shanghai 200063, China)
  • Online:2014-08-30 Published:2014-10-13
  • Contact: HUANG Zheng(黄征) E-mail:huang-zheng@sjtu.edu.cn

摘要: Waveform audio (WAV) file is a widely used file format of uncompressed audio. With the rapid development of digital media technology, one can easily insert duplicated segments with powerful audio editing software, e.g. inserting a segment of audio with negative meaning into the existing audio file. The duplicated segments can change the meaning of the audio file totally. So for a WAV file to be used as evidence in legal proceedings and historical documents, it is very importance to identify if there are any duplicated segments in it. This paper proposes a method to detect duplicated segments in a WAV file. Our method is based on the similarity calculation between two different segments. Duplicated segments are prone to having similar audio waveform, i.e., a high similarity. We use fast convolution algorithm to calculate the similarity, which makes our method quit efficient. We calculate the similarity between any two different segments in a digital audio file and use the similarity to judge which segments are duplicated. Experimental results show the feasibility and efficiency of our method on detecting duplicated audio segments.

关键词: duplicated audio segment, similarity, convolution

Abstract: Waveform audio (WAV) file is a widely used file format of uncompressed audio. With the rapid development of digital media technology, one can easily insert duplicated segments with powerful audio editing software, e.g. inserting a segment of audio with negative meaning into the existing audio file. The duplicated segments can change the meaning of the audio file totally. So for a WAV file to be used as evidence in legal proceedings and historical documents, it is very importance to identify if there are any duplicated segments in it. This paper proposes a method to detect duplicated segments in a WAV file. Our method is based on the similarity calculation between two different segments. Duplicated segments are prone to having similar audio waveform, i.e., a high similarity. We use fast convolution algorithm to calculate the similarity, which makes our method quit efficient. We calculate the similarity between any two different segments in a digital audio file and use the similarity to judge which segments are duplicated. Experimental results show the feasibility and efficiency of our method on detecting duplicated audio segments.

Key words: duplicated audio segment, similarity, convolution

中图分类号: