Detecting Fake-Quality WAV Audio Based on Phase Differences
With the continual growth of the requirements of digital audios, some people have been selling the fake-quality audio which was transcoded from the audio with worse quality and lower price for profits. For protecting the legitimate rights of consumers to some extent, a method for telling whether the WAV audio has been compressed with the audio encoders (MP3, AAC or OGG) is presented by using the statistical features of phase difference in this paper. The experimental results show that the proposed method can effectively detect whether the given WAV audio is original or not, and furthermore, it can identify the type of the codec. The overall hit rate can reach over 97 %.
KeywordsWAV Fake-quality detection Encoder type Phase differences
This work was supported by the National Natural Science Foundation of China (Grant No. 61170137, 61300055, 61301247), Zhejiang Natural Science Foundation (Grant No. LY13F020013), Ningbo Natural Science Foundation (Grant No. 2013A610057, 2013A610059), Ningbo University Fund (Grant No. XKXL1313, XKXL1310) and K.C. Wong Magna Fund in Ningbo University.
- 1.Information technology - coding of moving pictures and associated audio for digital storage media up to about 1.5 mbit/s – part 3: audio. ISO/IEC International Standard IS 11172-3 (1993)Google Scholar
- 2.Information technology - generic coding of moving pictures and associated audio information - part 7: advanced audio coding. ISO/IEC International Standard IS 13818-7 (1997)Google Scholar
- 3.Xiph.org: OGG. http://xiph.org/ogg/
- 4.Yang, R., Shi, Y.Q., Huang, J.W.: Defeating fake-quality MP3. In: Proceedings of the 11th ACM Workshop on Multimedia and Security, pp. 117–124 (2009)Google Scholar
- 6.Qiao, M.Y., Sung, A.H., Liu, Q.Z.: Revealing real quality of double compressed MP3 audio. In: Proceedings of the International Conference on Multimedia, pp. 1011–1014 (2010)Google Scholar
- 8.Bianchi, T., De Rosa, A., Fontani, M., et al.: Detection and classification of double compressed MP3 audio tracks. In: Proceedings of the first ACM Workshop on Information Hiding and Multimedia Security, pp. 159–164 (2013)Google Scholar
- 9.Luo, D., Luo, W., Yang, R., et al.: Compression history identification for digital audio signal. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1733–1736 (2012)Google Scholar
- 10.Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)Google Scholar
- 11.Lame MP3 Encoder. http://lame.sf.net
- 13.Rare Wares. http://www.rarewares.org/ogg-oggenc.php