2006:Audio Onset Detection Results: Solo Bars and Bells

From MIREX Wiki

Solo Bars and Bells Class - Peak F-measure Performance Across All Parameterizations

Contestant Parameters Total Correct Total FP Total FN Total Merged Total Doubled Avg. Correct Avg. FP Avg. FN Avg. Merged Avg. Doubled Avg. Precision Avg. Recall Avg. F-Measure
brossier_complex 0.5 309 12 15 0 0 103.0 4.0 5.0 0.0 0.0 0.962 0.854 0.877
brossier_dual 0.4 324 6 0 0 3 108.0 2.0 0.0 0.0 1.0 0.958 1.000 0.978
brossier_hfc 0.35 318 0 6 0 0 106.0 0.0 2.0 0.0 0.0 1.000 0.929 0.958
brossier_specdiff 0.4 306 6 18 0 0 102.0 2.0 6.0 0.0 0.0 0.946 0.891 0.917
dixon_cd (0.70/0.30) 312 30 12 0 0 104.0 10.0 4.0 0.0 0.0 0.849 0.987 0.890
dixon_nwpd (0.87/0.60) 324 261 0 0 6 108.0 87.0 0.0 0.0 2.0 0.429 1.000 0.543
dixon_rcd (0.70/0.70) 324 30 0 0 5 108.0 10.0 0.0 0.0 1.7 0.849 1.000 0.897
dixon_sf (0.90/0.55) 306 45 18 0 2 102.0 15.0 6.0 0.0 0.7 0.822 0.980 0.859
dixon_wpd (0.88/0.65) 318 33 6 0 0 106.0 11.0 2.0 0.0 0.0 0.789 0.929 0.830
du 0.7 228 0 96 0 0 76.0 0.0 32.0 0.0 0.0 1.000 0.893 0.932
roebel_1 0.09 321 0 3 2 0 107.0 0.0 1.0 0.7 0.0 1.000 0.997 0.998
roebel_2 0.12 315 0 9 2 0 105.0 0.0 3.0 0.7 0.0 1.000 0.974 0.986
roebel_3 0.12 321 0 3 2 0 107.0 0.0 1.0 0.7 0.0 1.000 0.997 0.998

download these results as csv

Solo Bars and Bells Class - Precision vs. Recall Curves

File:Solo bars and bells all runs.png