Description-based speech generation on AC-filt (test)
0.489JointCLAPAUDIOBOX
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AUDIOBOX2023.12 | 0.489 | 5.2 | — | — | |
| ground truth2023.12 | 0.479 | 23.5 | — | — | |
| VoiceLDM2023.12 | 0.449 | 6.8 | — | — | |
| AudioLDM2-SP2023.12 | 0.225 | 26.3 | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| AUDIOBOX2023.12 | 0.489 | 5.2 | — | — | |
| ground truth2023.12 | 0.479 | 23.5 | — | — | |
| VoiceLDM2023.12 | 0.449 | 6.8 | — | — | |
| AudioLDM2-SP2023.12 | 0.225 | 26.3 | — | — |