Difference between revisions of "2016:Audio Downbeat Estimation Results"
From MIREX Wiki
(→Runtime) |
|||
(12 intermediate revisions by 2 users not shown) | |||
Line 18: | Line 18: | ||
|- | |- | ||
! KB1 | ! KB1 | ||
− | | | + | | babeats13 || style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2016/KBDW1.pdf PDF] || Florian Krebs, Sebastian Böck |
|- | |- | ||
! KB2 | ! KB2 | ||
− | | | + | | babeats15 || style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2016/FK3.pdf PDF] || Florian Krebs, Sebastian Böck |
|- | |- | ||
! BK4 | ! BK4 | ||
Line 43: | Line 43: | ||
! Precision | ! Precision | ||
! Recall | ! Recall | ||
+ | |- | ||
+ | | BK4* | ||
+ | | 0.908 | ||
+ | | 0.906 | ||
+ | | 0.917 | ||
+ | |- | ||
+ | | KB1* | ||
+ | | 0.898 | ||
+ | | 0.888 | ||
+ | | 0.917 | ||
+ | |- | ||
+ | | KB2* | ||
+ | | 0.860 | ||
+ | | 0.853 | ||
+ | | 0.890 | ||
|- | |- | ||
| DBDR1* | | DBDR1* | ||
Line 54: | Line 69: | ||
| 0.804 | | 0.804 | ||
|- | |- | ||
− | | | + | | DSR1 |
− | | 0. | + | | 0.463 |
− | | 0. | + | | 0.476 |
− | | 0. | + | | 0.468 |
|- | |- | ||
| CD4 | | CD4 | ||
Line 63: | Line 78: | ||
| 0.416 | | 0.416 | ||
| 0.419 | | 0.419 | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|} | |} | ||
Line 87: | Line 87: | ||
! Precision | ! Precision | ||
! Recall | ! Recall | ||
− | |||
− | |||
− | |||
− | |||
− | |||
|- | |- | ||
| DBDR2* | | DBDR2* | ||
| 0.872 | | 0.872 | ||
| 0.861 | | 0.861 | ||
− | | 0.909 | + | | 0.909 |
|- | |- | ||
| BK4* | | BK4* | ||
Line 103: | Line 98: | ||
| 0.876 | | 0.876 | ||
|- | |- | ||
− | | | + | | DBDR1 |
− | | 0. | + | | 0.849 |
− | | 0. | + | | 0.861 |
− | | 0. | + | | 0.868 |
|- | |- | ||
− | | | + | | KB2* |
− | | 0. | + | | 0.818 |
− | | 0. | + | | 0.799 |
− | | 0. | + | | 0.870 |
|- | |- | ||
| KB1 | | KB1 | ||
| 0.803 | | 0.803 | ||
| 0.776 | | 0.776 | ||
− | | 0.859 | + | | 0.859 |
|- | |- | ||
− | | | + | | DSR1 |
− | | 0. | + | | 0.665 |
− | | 0. | + | | 0.646 |
− | | 0. | + | | 0.708 |
+ | |- | ||
+ | | CD4 | ||
+ | | 0.604 | ||
+ | | 0.586 | ||
+ | | 0.642 | ||
|- | |- | ||
|} | |} | ||
− | |||
{| class="wikitable sortable" border="1" | {| class="wikitable sortable" border="1" | ||
Line 134: | Line 133: | ||
! Recall | ! Recall | ||
|- | |- | ||
− | | | + | | BK4* |
− | | 0. | + | | 0.369 |
− | | 0. | + | | 0.290 |
− | | 0. | + | | 0.566 |
+ | |- | ||
+ | | KB2* | ||
+ | | 0.330 | ||
+ | | 0.263 | ||
+ | | 0.487 | ||
+ | |- | ||
+ | | KB1 | ||
+ | | 0.269 | ||
+ | | 0.221 | ||
+ | | 0.380 | ||
|- | |- | ||
| DBDR2 | | DBDR2 | ||
| 0.231 | | 0.231 | ||
| 0.194 | | 0.194 | ||
− | | 0.330 | + | | 0.330 |
|- | |- | ||
− | | | + | | DBDR1 |
− | | 0. | + | | 0.201 |
− | | 0. | + | | 0.199 |
− | | 0. | + | | 0.240 |
|- | |- | ||
| CD4 | | CD4 | ||
Line 158: | Line 167: | ||
| 0.155 | | 0.155 | ||
| 0.251 | | 0.251 | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|} | |} | ||
− | |||
{| class="wikitable sortable" border="1" | {| class="wikitable sortable" border="1" | ||
Line 179: | Line 177: | ||
! Recall | ! Recall | ||
|- | |- | ||
− | | | + | | BK4* |
− | | 0. | + | | 0.537 |
− | | 0. | + | | 0.468 |
− | | 0. | + | | 0.729 |
|- | |- | ||
| DBDR2 | | DBDR2 | ||
| 0.415 | | 0.415 | ||
| 0.360 | | 0.360 | ||
− | | 0.554 | + | | 0.554 |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|- | |- | ||
| KB1 | | KB1 | ||
| 0.352 | | 0.352 | ||
| 0.301 | | 0.301 | ||
− | | 0.498 | + | | 0.498 |
|- | |- | ||
| KB2* | | KB2* | ||
Line 213: | Line 196: | ||
| 0.269 | | 0.269 | ||
| 0.513 | | 0.513 | ||
+ | |- | ||
+ | | DSR1 | ||
+ | | 0.317 | ||
+ | | 0.281 | ||
+ | | 0.411 | ||
+ | |- | ||
+ | | DBDR1 | ||
+ | | 0.306 | ||
+ | | 0.292 | ||
+ | | 0.379 | ||
+ | |- | ||
+ | | CD4 | ||
+ | | 0.218 | ||
+ | | 0.186 | ||
+ | | 0.291 | ||
|} | |} | ||
− | |||
{| class="wikitable sortable" border="1" | {| class="wikitable sortable" border="1" | ||
− | |||
|+ Results cretan dataset | |+ Results cretan dataset | ||
|- | |- | ||
Line 224: | Line 220: | ||
! Precision | ! Precision | ||
! Recall | ! Recall | ||
+ | |- | ||
+ | | BK4* | ||
+ | | 0.635 | ||
+ | | 0.951 | ||
+ | | 0.476 | ||
+ | |- | ||
+ | | KB2* | ||
+ | | 0.443 | ||
+ | | 0.661 | ||
+ | | 0.334 | ||
+ | |- | ||
+ | | KB1 | ||
+ | | 0.433 | ||
+ | | 0.641 | ||
+ | | 0.328 | ||
|- | |- | ||
| DBDR1 | | DBDR1 | ||
Line 235: | Line 246: | ||
| 0.311 | | 0.311 | ||
|- | |- | ||
− | | | + | | DSR1 |
− | | 0. | + | | 0.265 |
− | | 0. | + | | 0.398 |
− | | 0. | + | | 0.199 |
|- | |- | ||
| CD4 | | CD4 | ||
Line 244: | Line 255: | ||
| 0.377 | | 0.377 | ||
| 0.188 | | 0.188 | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|} | |} | ||
− | |||
{| class="wikitable sortable" border="1" | {| class="wikitable sortable" border="1" | ||
Line 270: | Line 265: | ||
! Recall | ! Recall | ||
|- | |- | ||
− | | | + | | BK4* |
− | | 0. | + | | 0.970 |
− | | 0. | + | | 0.970 |
− | | 0. | + | | 0.970 |
+ | |- | ||
+ | | KB2* | ||
+ | | 0.851 | ||
+ | | 0.854 | ||
+ | | 0.848 | ||
+ | |- | ||
+ | | KB1 | ||
+ | | 0.690 | ||
+ | | 0.693 | ||
+ | | 0.688 | ||
|- | |- | ||
| DBDR2 | | DBDR2 | ||
| 0.629 | | 0.629 | ||
| 0.628 | | 0.628 | ||
− | | 0.638 | + | | 0.638 |
|- | |- | ||
− | | | + | | DBDR1 |
− | | 0. | + | | 0.578 |
− | | 0. | + | | 0.613 |
− | | 0. | + | | 0.561 |
|- | |- | ||
| CD4 | | CD4 | ||
Line 294: | Line 299: | ||
| 0.232 | | 0.232 | ||
| 0.196 | | 0.196 | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|} | |} | ||
Line 313: | Line 308: | ||
! Precision | ! Precision | ||
! Recall | ! Recall | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|- | |- | ||
| BK4* | | BK4* | ||
| 0.599 | | 0.599 | ||
| 0.659 | | 0.659 | ||
− | | 0.598 | + | | 0.598 |
|- | |- | ||
− | | | + | | DBDR2* |
− | | 0. | + | | 0.532 |
− | | 0. | + | | 0.539 |
− | | 0. | + | | 0.574 |
|- | |- | ||
− | | | + | | DBDR1* |
− | | 0. | + | | 0.527 |
− | | 0. | + | | 0.570 |
− | | 0. | + | | 0.529 |
|- | |- | ||
| KB1 | | KB1 | ||
Line 348: | Line 333: | ||
| 0.459 | | 0.459 | ||
| 0.444 | | 0.444 | ||
+ | |- | ||
+ | | DSR1 | ||
+ | | 0.251 | ||
+ | | 0.260 | ||
+ | | 0.279 | ||
+ | |- | ||
+ | | CD4 | ||
+ | | 0.174 | ||
+ | | 0.189 | ||
+ | | 0.185 | ||
|} | |} | ||
Line 358: | Line 353: | ||
! Recall | ! Recall | ||
|- | |- | ||
− | | | + | | KB2 |
− | | 0. | + | | 0.647 |
− | | 0. | + | | 0.665 |
− | | 0. | + | | 0.653 |
+ | |- | ||
+ | | BK4 | ||
+ | | 0.638 | ||
+ | | 0.636 | ||
+ | | 0.669 | ||
+ | |- | ||
+ | | KB1 | ||
+ | | 0.630 | ||
+ | | 0.647 | ||
+ | | 0.634 | ||
|- | |- | ||
| DBDR2 | | DBDR2 | ||
| 0.619 | | 0.619 | ||
| 0.628 | | 0.628 | ||
− | | 0.666 | + | | 0.666 |
|- | |- | ||
− | | | + | | DBDR1 |
− | | 0. | + | | 0.615 |
− | | 0. | + | | 0.651 |
− | | 0. | + | | 0.631 |
|- | |- | ||
| CD4 | | CD4 | ||
Line 382: | Line 387: | ||
| 0.397 | | 0.397 | ||
| 0.423 | | 0.423 | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|} | |} | ||
Line 397: | Line 392: | ||
= Runtime = | = Runtime = | ||
− | + | The runtime is measured for the *hjdb* dataset (duration 3h19m) and then extrapolated to the duration of all datasets (total 38h51m). For measuring runtimes, we used a PC with four i5-2400 CPUs @ 3.10GHz. | |
+ | |||
+ | {| class="wikitable" border="1" | ||
+ | |- | ||
+ | ! Algorithm | ||
+ | ! Multi-core | ||
+ | ! Runtime hjdb [mm] | ||
+ | ! Extrapolated runtime all [hh] | ||
+ | ! x times faster than realtime | ||
+ | |- | ||
+ | | DBDRx | ||
+ | | yes | ||
+ | | 86.8 | ||
+ | | 16.9 | ||
+ | | 2.29 | ||
+ | |- | ||
+ | | KBx | ||
+ | | yes | ||
+ | | 22.8 | ||
+ | | 4.45 | ||
+ | | 8.72 | ||
+ | |- | ||
+ | | BK4 | ||
+ | | yes | ||
+ | | 13.1 | ||
+ | | 2.55 | ||
+ | | 15.2 | ||
+ | |- | ||
+ | | DSR1 | ||
+ | | no | ||
+ | | 4.5 | ||
+ | | 0.88 | ||
+ | | 44.2 | ||
+ | |- | ||
+ | | CD4 | ||
+ | | no | ||
+ | | 3.1 | ||
+ | | 0.6 | ||
+ | | 63.5 | ||
+ | |- | ||
+ | |} |
Latest revision as of 09:00, 24 August 2016
Submitted Algorithms
Submission code | Submission name | Abstract | Contributors |
---|---|---|---|
DBDR1 | DB1_no_beatles | Simon Durand, Juan Bello, Bertrand David, Gael Richard | |
DBDR2 | DB2_no_ballroom | Simon Durand, Juan Bello, Bertrand David, Gael Richard | |
KB1 | babeats13 | Florian Krebs, Sebastian Böck | |
KB2 | babeats15 | Florian Krebs, Sebastian Böck | |
BK4 | joint_tracker | Sebastian Böck, Florian Krebs | |
DSR1 | downbeater | Matthew Davies, Adam Stark, Andrew Robertson | |
CD4 | qm-barbeattracker | Matthew Davies, Chris Cannam |
Results
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.908 | 0.906 | 0.917 |
KB1* | 0.898 | 0.888 | 0.917 |
KB2* | 0.860 | 0.853 | 0.890 |
DBDR1* | 0.838 | 0.874 | 0.846 |
DBDR2 | 0.783 | 0.808 | 0.804 |
DSR1 | 0.463 | 0.476 | 0.468 |
CD4 | 0.412 | 0.416 | 0.419 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
DBDR2* | 0.872 | 0.861 | 0.909 |
BK4* | 0.865 | 0.872 | 0.876 |
DBDR1 | 0.849 | 0.861 | 0.868 |
KB2* | 0.818 | 0.799 | 0.870 |
KB1 | 0.803 | 0.776 | 0.859 |
DSR1 | 0.665 | 0.646 | 0.708 |
CD4 | 0.604 | 0.586 | 0.642 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.369 | 0.290 | 0.566 |
KB2* | 0.330 | 0.263 | 0.487 |
KB1 | 0.269 | 0.221 | 0.380 |
DBDR2 | 0.231 | 0.194 | 0.330 |
DBDR1 | 0.201 | 0.199 | 0.240 |
CD4 | 0.186 | 0.154 | 0.258 |
DSR1 | 0.184 | 0.155 | 0.251 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.537 | 0.468 | 0.729 |
DBDR2 | 0.415 | 0.360 | 0.554 |
KB1 | 0.352 | 0.301 | 0.498 |
KB2* | 0.336 | 0.269 | 0.513 |
DSR1 | 0.317 | 0.281 | 0.411 |
DBDR1 | 0.306 | 0.292 | 0.379 |
CD4 | 0.218 | 0.186 | 0.291 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.635 | 0.951 | 0.476 |
KB2* | 0.443 | 0.661 | 0.334 |
KB1 | 0.433 | 0.641 | 0.328 |
DBDR1 | 0.426 | 0.715 | 0.308 |
DBDR2 | 0.418 | 0.637 | 0.311 |
DSR1 | 0.265 | 0.398 | 0.199 |
CD4 | 0.250 | 0.377 | 0.188 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.970 | 0.970 | 0.970 |
KB2* | 0.851 | 0.854 | 0.848 |
KB1 | 0.690 | 0.693 | 0.688 |
DBDR2 | 0.629 | 0.628 | 0.638 |
DBDR1 | 0.578 | 0.613 | 0.561 |
CD4 | 0.334 | 0.341 | 0.329 |
DSR1 | 0.208 | 0.232 | 0.196 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
BK4* | 0.599 | 0.659 | 0.598 |
DBDR2* | 0.532 | 0.539 | 0.574 |
DBDR1* | 0.527 | 0.570 | 0.529 |
KB1 | 0.436 | 0.475 | 0.447 |
KB2* | 0.428 | 0.459 | 0.444 |
DSR1 | 0.251 | 0.260 | 0.279 |
CD4 | 0.174 | 0.189 | 0.185 |
Algorithm | F-Measure | Precision | Recall |
---|---|---|---|
KB2 | 0.647 | 0.665 | 0.653 |
BK4 | 0.638 | 0.636 | 0.669 |
KB1 | 0.630 | 0.647 | 0.634 |
DBDR2 | 0.619 | 0.628 | 0.666 |
DBDR1 | 0.615 | 0.651 | 0.631 |
CD4 | 0.460 | 0.461 | 0.482 |
DSR1 | 0.397 | 0.397 | 0.423 |
*) Rows marked by an asterisk should be taken with care as in those cases overlapping test and training sets were used. This could lead to overestimated metrics.
Runtime
The runtime is measured for the *hjdb* dataset (duration 3h19m) and then extrapolated to the duration of all datasets (total 38h51m). For measuring runtimes, we used a PC with four i5-2400 CPUs @ 3.10GHz.
Algorithm | Multi-core | Runtime hjdb [mm] | Extrapolated runtime all [hh] | x times faster than realtime |
---|---|---|---|---|
DBDRx | yes | 86.8 | 16.9 | 2.29 |
KBx | yes | 22.8 | 4.45 | 8.72 |
BK4 | yes | 13.1 | 2.55 | 15.2 |
DSR1 | no | 4.5 | 0.88 | 44.2 |
CD4 | no | 3.1 | 0.6 | 63.5 |