Emotion and Style Control Speech Generation on ESD
82.1ESD ScoreMiniCPM-o 4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| MiniCPM-o 4.5Neutral reference audio=true2026.04 | 82.1 | |
| CosyVoice2Neutral reference audio=true2026.04 | 53.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| MiniCPM-o 4.5Neutral reference audio=true2026.04 | 82.1 | |
| CosyVoice2Neutral reference audio=true2026.04 | 53.4 |