2007:Audio Music Mood Classification Results

From MIREX Wiki
Revision as of 11:44, 26 July 2010 by Singh14 (talk | contribs) (Team ID)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Introduction

These are the results for the 2007 running of the Audio Music Mood Classification task. For background information about this task set please refer to the 2007:Audio Music Mood Classification page. The data set consisted of 600 30 second audio clips evenly divided into 5 general moods. The assignment of moods to files was done by human evaluators with a file accepted as a representative of a given mood when at least 2 graders concurred in the assignment.

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
CL = Cyril Laurier, Perfecto Herrera
IM = IMIRSEL M2K
KL = Kyogu Lee

Overall Summary Results

MIREX 2007 Audio Mood Classification Summary Results - Raw Classification Accuracy Averaged Over Three Train/Test Folds

Participant Avg. Raw Classification Accuracy
IM_knn 47.17%
IM_svm 55.83%
CL 60.50%
KL_1 49.83%
KL_2 25.67%
TL 59.67%
ME 57.83%
ME_spec 55.83%
GT 61.50%

download these results as csv

MIREX 2007 Audio Artist Classification Evaluation Logs and Confusion Matrices

IM_knn
IM_svm
CL
KL_1
KL_2
TL
ME
ME_spec
GT

MIREX 2007 Audio Mood Classification Run Times

Participant Runtime (sec) / Fold
IM-knn Feat Ex: 535 Train/Classify: 74
IM-svm Feat Ex: 535 Train/Classify: 7
CL Feat Ex: 3605 Train/Classify: 7440
KL_1 Feat Ex: 353 Train/Classify: 204
KL_2 Feat Ex: 348 Train/Classify: 173
TL Feat Ex: 1597 Train/Classify: 12
ME Feat Ex: 613 Train/Classify: 2
ME_spec Feat Ex: 612 Train/Classify: 2
GT Feat Ex/Train/Classify: 122

download these results as csv