Song Describer Dataset
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Music Generation | Song Describer Dataset | FAD1.01 | 9 | |
| Intensity-controlled Audio Generation | Song Describer Dataset (test) | FDopenl369.9 | 5 | |
| Pitch-controlled Audio Generation | Song Describer Dataset (test) | FDopenl3163.24 | 5 | |
| Beats-controlled Audio Generation | Song Describer Dataset (test) | FDopenl3101.24 | 5 | |
| Text-to-Music Generation | Song Describer Dataset (full) | FD_openl372.17 | 5 | |
| Music Generation | Song Describer Dataset (test) | FDopenl3190.47 | 5 | |
| Pitch+Intensity-controlled Audio Generation | Song Describer Dataset (test) | FDopenl377.86 | 4 | |
| Beats+Intensity-controlled Audio Generation | Song Describer Dataset (test) | FDopenl3103.53 | 4 | |
| Music Generation | Song Describer Dataset no-singing | FDopenl378.7 | 4 | |
| Music Generation | Song Describer Dataset no-singing (test) | FDopenl379.09 | 4 | |
| Music Generation | Song Describer Dataset no-singing subset 4m 45s | Stereo Correctness100 | 2 |
Showing 11 of 11 rows