Zero-shot Text-to-Speech on Chinese Speech Emotion Prompt
0.0162WERIndexTTS2
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| IndexTTS22026.01 | 0.0162 | 0.0162 | 3.715 | 0.597 | 4.345 | 3.248 | — | — | — | |
| Segment-Aware Conditioning2026.01 | 0.0273 | 0.0273 | 3.803 | 0.578 | 4.536 | 3.291 | — | — | — | |
| MaskGCT2026.01 | 0.0814 | 0.0814 | 3.711 | 0.614 | 4.366 | 3.167 | — | — | — | |
| F5TTS2026.01 | 0.09 | 0.09 | 3.386 | 0.598 | 4.286 | 3.204 | — | — | — |