MP3 compression classification through audio analysis statistics

McFarlane J, Chakravarthi BR. MP3 compression classification through audio analysis statistics. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10558. Available from: https://aes.org/publications/elibrary-page/?id=21671

@inproceedings{McFarlane2022_21671,
  author = {McFarlane, Jamie and Chakravarthi, Bharathi Raja},
  title = {{MP3 compression classification through audio analysis statistics}},
  booktitle = {AES Convention 152},
  note = {Paper 10558},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21671}
}

TY  - CPAPER
TI  - MP3 compression classification through audio analysis statistics
AU  - McFarlane, Jamie
AU  - Chakravarthi, Bharathi Raja
T2  - AES Convention 152
M1  - Paper 10558
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21671
PB  - Audio Engineering Society
LA  - en
AB  - MP3 audio compression can be undesirable in circumstances where high-quality music presentation is required and there is a lack of automated, evidenced, and open-source methods to determine this. This study introduced a new and accessible approach to discriminate between compression levels and identify lossy audio transcoding. Machine learning classifiers were trained on feature sets of audio analysis statistics, derived from multiple step-wise re-encodings of compressed audio samples. Two classifiers, a stacked model and a XGBoost-based model, had comparable accuracies to previous examples in the literature and marketplace (Stacked: 0.947, XGBoost: 0.970, Literature reference: 0.965, Commercial reference: 0.980). For transcoded samples, which hide compression levels with post-processing, the new classifiers were less accurate than existing methods. However, all methods were inaccurate in identifying transcodes where artificial noise was added via the µ-law encoder. A command-line implementation is available at gitlab.com/jammcfar/kbps_detect_proto.
ER  -