List your company

Image-to-Audio Generation on BPSD

68.83Onset F1 (50ms)DAC Reconstruction
21.676433.918246.1658.4018May 19, 2025

Evaluation results

MethodLinks
DAC ReconstructionType=Upper-bound2025.0568.8382.3987.470.05
Multi-stageTraining Tasks/Data=OMR + Image-to-Audio + MIDI-to-Audio2025.0550.9170.479.960.137
Direct I2ATraining Tasks/Data=OMR + Image-to-Audio2025.0548.6764.374.010.098
Direct I2ATraining Tasks/Data=OMR + Image-to-Audio + MIDI-to-Audio2025.0548.3664.6374.920.081
Multi-stage: Zeus → VirtuosoNet → MSDMethod Components=Zeus, VirtuosoNet, MSD2025.0545.5259.3569.360.33
Direct I2ATraining Tasks/Data=YTSV-P (Image-to-Audio Only)2025.0523.4934.5144.150.422