Image-to-Audio Generation on YTSV T11 (test)
82.28Onset F1 (50ms)DAC Reconstruction
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| DAC ReconstructionType=Upper-bound2025.05 | 82.28 | 86.43 | 88.76 | 0.035 | |
| Direct I2ATraining Tasks/Data=OMR + Image-to-Audio + MIDI-to-Audio2025.05 | 52.66 | 68.45 | 76.24 | 0.055 | |
| Direct I2ATraining Tasks/Data=OMR + Image-to-Audio2025.05 | 51.6 | 67.92 | 75.98 | 0.056 | |
| Direct I2ATraining Tasks/Data=YTSV-P (Image-to-Audio Only)2025.05 | 27.05 | 43.32 | 53.02 | 0.317 |