Music Genre Categorization in Humans and Machines

Guaus E, Herrera P. Music Genre Categorization in Humans and Machines. In: AES Convention 121. Audio Engineering Society; 2006. Paper 6979. Available from: https://aes.org/publications/elibrary-page/?id=13813

@inproceedings{Guaus2006_13813,
  author = {Guaus, Enric and Herrera, Perfecto},
  title = {{Music Genre Categorization in Humans and Machines}},
  booktitle = {AES Convention 121},
  note = {Paper 6979},
  year = {2006},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13813}
}

TY  - CPAPER
TI  - Music Genre Categorization in Humans and Machines
AU  - Guaus, Enric
AU  - Herrera, Perfecto
T2  - AES Convention 121
M1  - Paper 6979
PY  - 2006
DA  - 2006/10/06
UR  - https://aes.org/publications/elibrary-page/?id=13813
PB  - Audio Engineering Society
LA  - en
AB  - Music Genre Classification is one of the most active tasks in Music Information Retrieval (MIR). Many successful approaches can be found in literature. Most of them are based on Machine Learning algorithms applied to different audio features automatically computed for a specific database. But there is no computational model that explains how musical features are combined in order to yield genre decision in humans. In this work we present a listening experiment where audio has been altered in order to preserve some properties of music (rhythm, harmony, etc) but at the same time degrading other ones. Results are compared with a series of state-of-the-art genre classifiers based on these musical properties and we draw some lessons from that comparison.
ER  -