Using Audio Classifiers as a Mechanism for Content-Based Song Similarity

Fields B, Casey M. Using Audio Classifiers as a Mechanism for Content-Based Song Similarity. In: AES Convention 123. Audio Engineering Society; 2007. Paper 7267. Available from: https://aes.org/publications/elibrary-page/?id=14325

@inproceedings{Fields2007_14325,
  author = {Fields, Benjamin and Casey, Michael},
  title = {{Using Audio Classifiers as a Mechanism for Content-Based Song Similarity}},
  booktitle = {AES Convention 123},
  note = {Paper 7267},
  year = {2007},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14325}
}

TY  - CPAPER
TI  - Using Audio Classifiers as a Mechanism for Content-Based Song Similarity
AU  - Fields, Benjamin
AU  - Casey, Michael
T2  - AES Convention 123
M1  - Paper 7267
PY  - 2007
DA  - 2007/10/06
UR  - https://aes.org/publications/elibrary-page/?id=14325
PB  - Audio Engineering Society
LA  - en
AB  - As collections of digital music become larger and more widespread, there is a growing need for assistance in a user's navigation and interaction with a collection and with the individual members of that collection. Examining pairwise song relationships and similarities, based upon content derived features, provides a useful tool to do so. This paper looks into a means of extending a song classification algorithm to provide song to song similarity information. In order to evaluate the effectiveness of this method, the similarity data is used to group the songs into k-means clusters, these clusters are then compared against the original genre sorting algorithm.
ER  -