MAESTRO
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Automatic Piano Transcription | MAESTRO v3.0.0 (test) | Note F1 Score (w/ Offset)93.48 | 19 | |
| Packet Loss Concealment | MAESTRO Solo Piano 50-minute file (single file per loss rate) | pkt-NMSE0 | 18 | |
| Piano Transcription | MAESTRO | Precision96.6 | 14 | |
| Integer Regression | MAESTRO (test) | RMSE32 | 13 | |
| Blending | Maestro (test) | FAD2.708 | 8 | |
| Audio Inpainting | MAESTRO | ODG (PEA-Q)-3.318 | 8 | |
| Music Transcription | MAESTRO HEAR challenge | Onset FMS0.391 | 8 | |
| Conditional Generation | Maestro (test) | FAD0.667 | 7 | |
| Audio Watermarking | MAESTRO | Detectability Accuracy100 | 7 | |
| Unconditional Symbolic Music Generation | Maestro | Used Pitch Coverage0.905 | 7 | |
| MIDI transcription | MAESTRO 177 files (test) | Note F1 Score98.3 | 6 | |
| Audio-MIDI Retrieval | MAESTRO long-horizon (train) | Best S (%)83.8 | 6 | |
| Audio Generation | MAESTRO (test) | FAD (unconditional)0.131 | 6 | |
| Piano Transcription | MAESTRO (test) | Frame Precision93.1 | 6 | |
| Automatic Piano Transcription (Onset & Offset) | MAESTRO | Precision94.61 | 5 | |
| Sustain Pedal Transcription | Maestro v3.0.0 (test) | Activation Precision96.69 | 5 | |
| Music transcription | MAESTRO | Onset FMS0.391 | 5 | |
| Music Transcription | MAESTRO | Precision99.64 | 5 | |
| Pedal Transcription | MAESTRO (test) | Frame Precision94.41 | 5 | |
| Membership Inference Attack | MAESTRO v3 | AUC0.91 | 4 | |
| Retrieval | MAESTRO | Mean S Score (%)84 | 4 | |
| Automatic Music Transcription | MAESTRO (test) | Note Onset F189.7 | 4 | |
| Audio Inpainting | MAESTRO (test) | MOS4.12 | 4 | |
| Unconditional Music Generation | MAESTRO | Selection Rate95.8 | 4 | |
| Music Modeling | MAESTRO controls | Loss0.921 | 3 |
Showing 25 of 32 rows