Feature Selection vs. Feature Space Transformation in Music Genre Classification Framework

Lukashevich H. Feature Selection vs. Feature Space Transformation in Music Genre Classification Framework. In: AES Convention 126. Audio Engineering Society; 2009. Paper 7655. Available from: https://aes.org/publications/elibrary-page/?id=14851

@inproceedings{Lukashevich2009_14851,
  author = {Lukashevich, Hanna},
  title = {{Feature Selection vs. Feature Space Transformation in Music Genre Classification Framework}},
  booktitle = {AES Convention 126},
  note = {Paper 7655},
  year = {2009},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14851}
}

TY  - CPAPER
TI  - Feature Selection vs. Feature Space Transformation in Music Genre Classification Framework
AU  - Lukashevich, Hanna
T2  - AES Convention 126
M1  - Paper 7655
PY  - 2009
DA  - 2009/05/06
UR  - https://aes.org/publications/elibrary-page/?id=14851
PB  - Audio Engineering Society
LA  - en
AB  - Automatic classification of music genres is an inherent field of music information retrieval research. Nearly all state-of-the-art music genre recognition systems start from the feature extraction block. The extracted acoustical features often could be correlated or/and redundant, which can course various difficulties on the classification stage. In this paper we present a comparative analysis on applying supervised Feature Selection and Feature Space Transformation algorithms to reduce the feature dimensionality. We discuss pro and contra of the methods and weigh the benefits of each one against the others.
ER  -