From MIREX Wiki
Introduction
These are the results for the 2009 running of the Audio Onset Detection. For background information about this task set please refer to the 2009:Audio_Onset_detection page.
The aim of the Audio Onset Detection task is to find the time locations at which all musical events in a recording begin. The dataset consists of 85 recordings across 9 different "classes" (e.g. solo drums, polyphonic pitched, etc.). For each sound file, ground truth annotations produced by 3-5 listeners were used for the evaluation.
General Legend
Team ID
AR1 = A. Röbel (7_hd)
AR2 = A. Röbel (10_hd)
AR3 = A. Röbel (12_nhd)
AR4 = A. Röbel (16_nhd)
AR5 = A. Röbel (19_hdc)
GT = George Tzanetakis
PI = Antonio Pertusa, José M. Iñesta
TZC1 = Hui Li Tan, Yongwei Zhu, Lekha Chaisorn
TZC2 = Hui Li Tan, Yongwei Zhu, Lekha Chaisorn
TZC3 = Hui Li Tan, Yongwei Zhu, Lekha Chaisorn
TZC4 = Hui Li Tan, Yongwei Zhu, Lekha Chaisorn
TZC5 = Hui Li Tan, Yongwei Zhu, Lekha Chaisorn
Overall Summary Results
MIREX 2009 Audio Onset Detection Summary Results - Peak F-measure performance across all parameterizations
| Contestant |
Parameters |
Class |
# Files in Class |
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 |
| AR1 |
0.34 |
Total |
85 |
7560 |
2736 |
1795 |
188 |
257 |
26.06196078 |
9.396862745 |
5.853333333 |
0.583137255 |
0.783921569 |
0.813172379 |
0.833011441 |
0.789965992 |
| AR2 |
0.43 |
Total |
85 |
7015 |
1231 |
2340 |
161 |
133 |
24.49764706 |
4.349411765 |
7.417647059 |
0.514901961 |
0.469803922 |
0.850044452 |
0.791942348 |
0.795994316 |
| AR3 |
0.28 |
Total |
85 |
6440 |
901 |
2915 |
145 |
198 |
22.44784314 |
3.140392157 |
9.46745098 |
0.458039216 |
0.636862745 |
0.859574741 |
0.731492668 |
0.760988355 |
| AR4 |
0.13 |
Total |
85 |
6426 |
846 |
2929 |
148 |
183 |
22.48196078 |
2.929803922 |
9.433333333 |
0.474901961 |
0.571764706 |
0.863924132 |
0.73621974 |
0.764809169 |
| AR5 |
0.34 |
Total |
85 |
7339 |
2367 |
2016 |
185 |
212 |
25.33176471 |
8.138823529 |
6.583529412 |
0.579215686 |
0.640784314 |
0.805554596 |
0.818797553 |
0.783117795 |
| GT |
N/A |
Total |
85 |
5053 |
2836 |
4302 |
162 |
46 |
17.47607843 |
9.653333333 |
14.43921569 |
0.510196078 |
0.164705882 |
0.670059391 |
0.599119129 |
0.595419443 |
| PI |
0.25 |
Total |
85 |
6861 |
2232 |
2494 |
196 |
10 |
23.93039216 |
7.693137255 |
7.984901961 |
0.62745098 |
0.029803922 |
0.799872471 |
0.774985554 |
0.767893739 |
| TZC1 |
N/A |
Total |
85 |
6882 |
2224 |
2473 |
157 |
308 |
24.17137255 |
7.805098039 |
7.743921569 |
0.48745098 |
1.079215686 |
0.756722619 |
0.769681153 |
0.744344246 |
| TZC2 |
N/A |
Total |
85 |
6588 |
1976 |
2767 |
152 |
266 |
23.2654902 |
7.193333333 |
8.649803922 |
0.478823529 |
0.967843137 |
0.782791592 |
0.745809848 |
0.733830105 |
| TZC3 |
N/A |
Total |
85 |
5961 |
1703 |
3394 |
146 |
285 |
21.25215686 |
6.571372549 |
10.66313725 |
0.46 |
1.044313725 |
0.796136559 |
0.689654254 |
0.686300505 |
| TZC4 |
N/A |
Total |
85 |
5953 |
1843 |
3402 |
135 |
345 |
21.23254902 |
7.108627451 |
10.6827451 |
0.421568627 |
1.28745098 |
0.789783639 |
0.689112046 |
0.679377579 |
| TZC5 |
N/A |
Total |
85 |
7816 |
5502 |
1539 |
84 |
1540 |
26.9745098 |
19.8372549 |
4.940784314 |
0.284313725 |
5.157254902 |
0.628808252 |
0.836869809 |
0.682325286 |
download these results as csv
MIREX 2009 Audio Onset Detection Runtime Data
| Participant |
Machine |
Runtime (hh:mm) |
| AR1 |
ALE |
00:03 |
| AR2 |
ALE |
00:04 |
| AR3 |
ALE |
00:02 |
| AR4 |
ALE |
00:02 |
| AR5 |
ALE |
00:03 |
| GT |
ALE |
00:01 |
| PI |
ALE |
00:01 |
| TZC1 |
ALE |
01:57 |
| TZC2 |
ALE |
01:57 |
| TZC3 |
ALE |
01:57 |
| TZC4 |
ALE |
01:57 |
| TZC5 |
ALE |
01:57 |
download these results as csv
Results by Class
Individual Results
