| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-speaker dialog synthesis | COVOMIX2-DIALOGUE-20S | cpWER0.145 | 6 | |
| Multi-speaker Dialogue Synthesis | CoVoMix2 Dialogue-WildRef 50 dialogs paired with 30 in-the-wild reference clips (test) | cpWER0.156 | 6 | |
| Human Evaluation | CoVOMIX2-DIALOGUE-20S and CoVOMIX2-DIALOGUE-WILDREF mix | Win Rate (SCENA Preferred)84.6 | 4 |