The Effects of Lossy Audio Encoding on Genre Classification Tasks

Casey M, Fields B, Jacobson K, Sandler M. The Effects of Lossy Audio Encoding on Genre Classification Tasks. In: AES Convention 124. Audio Engineering Society; 2008. Paper 7417. Available from: https://aes.org/publications/elibrary-page/?id=14547

@inproceedings{Casey2008_14547,
  author = {Casey, Michael and Fields, Ben and Jacobson, Kurt and Sandler, Mark},
  title = {{The Effects of Lossy Audio Encoding on Genre Classification Tasks}},
  booktitle = {AES Convention 124},
  note = {Paper 7417},
  year = {2008},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14547}
}

TY  - CPAPER
TI  - The Effects of Lossy Audio Encoding on Genre Classification Tasks
AU  - Casey, Michael
AU  - Fields, Ben
AU  - Jacobson, Kurt
AU  - Sandler, Mark
T2  - AES Convention 124
M1  - Paper 7417
PY  - 2008
DA  - 2008/05/06
UR  - https://aes.org/publications/elibrary-page/?id=14547
PB  - Audio Engineering Society
LA  - en
AB  - In large audio collections, it is common to store audio content using perceptual encoding. However, encoding parameters may vary from collection to collection or even within a collection - using different bit rates, sample rates, codecs, etc. We evaluate the effect of various lossy audio encodings on the application of audio spectrum projection features to the automatic genre classification tasks. We show that decreases in mean classification accuracy, while small, are statistically significant for bit-rates of 96kbps or lower. Also, a heterogeneous collection of audio encodings has statistically significant decreases in mean classification accuracy compared to a pure PCM collection.
ER  -