Detection of Genuine Lossless Audio Files: Application to the MPEG-AAC Codec

Derrien O. Detection of Genuine Lossless Audio Files: Application to the MPEG-AAC Codec. J Audio Eng Soc. 2019;67(3):116-123. doi:10.17743/jaes.2019.0002

@article{Derrien2019_19892,
  author = {Derrien, Olivier},
  title = {{Detection of Genuine Lossless Audio Files: Application to the MPEG-AAC Codec}},
  journal = {Journal of the Audio Engineering Society},
  volume = {67},
  number = {3},
  pages = {116--123},
  url = {https://doi.org/10.17743/jaes.2019.0002},
  doi = {10.17743/jaes.2019.0002},
  year = {2019},
  month = mar,
  publisher = {Audio Engineering Society}
}

TY  - JOUR
TI  - Detection of Genuine Lossless Audio Files: Application to the MPEG-AAC Codec
AU  - Derrien, Olivier
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 67
IS  - 3
SP  - 116
EP  - 123
PY  - 2019
DA  - 2019/03/06
DO  - 10.17743/jaes.2019.0002
UR  - https://doi.org/10.17743/jaes.2019.0002
PB  - Audio Engineering Society
LA  - en
AB  - In this study the author describes an algorithm that can discriminate transcoded from true lossless audio files, i.e. a file that was obtained by directly ripping a genuine audio CD from a file that was decoded from a lossy audio format (e.g. MP3, AAC) and re-encoded with a lossless format. This algorithm should allow both consumers and online music dealers to check the authenticity of lossless music files. Although research focuses on the MPEG AAC codec, the approach can also be applied to the MP3 codec. It is based on the detection of quantization errors in the time-frequency domain without using machine learning. Tests with a large database of 1576 audio files, original and transcoded with AAC from iTunes, show null false positive ratios and very low false negative ratios, possibly null for high-precision settings, which is better than other methods. It was shown that a perfectly accurate classification can be reached, provided a sufficiently long computation time is allowed. Furthermore, the method is naturally immune to truncation of audio files and global gain modification.
ER  -