2007:Audio Artist Identification Results
From MIREX Wiki
Revision as of 18:40, 13 May 2010 by IMIRSELBot (talk | contribs) (Robot: Automated text replacement (-<csv([^>]*)> +<csv\1>2007/))
Contents
Introduction
These are the results for the 2007 running of the Audio Artist Identification task. For background information about this task set please refer to the 2007:Audio Artist Identification page. The data set was 3060 30 second clips representing 102 different recording artists.
General Legend
Team ID
ME = Michael I. Mandel, Daniel P. W. Ellis
TL = Thomas Lidy, Andreas Rauber, Antonio Pertusa, José Manuel Iñesta
GT = George Tzanetakis
KL = Kyogu Lee
IM = IMIRSEL M2K
Overall Summary Results
MIREX 2007 Audio Artist Classification Summary Results - Raw Classification Accuracy Averaged Over Three Train/Test Folds
| Participant | Avg. Raw Classification Accuracy |
|---|---|
| IM_knn | 35.29% |
| IM_svm | 48.14% |
| KL | 9.71% |
| TL | 38.76% |
| ME | 40.46% |
| ME_spec | 47.16% |
| GT | 36.70% |
MIREX 2007 Audio Artist Classification Evaluation Logs and Confusion Matrices
IM_knn
IM_svm
KL
TL
ME
ME_spec
GT
MIREX 2007 Audio Artist Classification Run Times
| Participant | Runtime (sec) / Fold |
|---|---|
| IM-knn | Feat Ex: 2760 Train/Classify: 245 |
| IM-svm | Feat Ex: 2760 Train/Classify: 188 |
| KL | Feat Ex: 1806 Train/Classify: 4664 |
| TL | Feat Ex: 23631 Train/Classify: 4764 |
| ME | Feat Ex: 3403 Train/Classify: 65 |
| ME_spec | Feat Ex: 3382 Train/Classify: 64 |
| GT | Feat Ex/Train/Classify: 632 |
