Zero-shot Text-to-Speech on English Speech Emotion Prompt
0.0194WERF5TTS
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| F5TTS2026.01 | 0.0194 | 0.0194 | 3.683 | 0.543 | 4.454 | 3.307 | — | — | — | |
| MaskGCT2026.01 | 0.0248 | 0.0248 | 3.964 | 0.539 | 4.536 | 3.301 | — | — | — | |
| IndexTTS22026.01 | 0.026 | 0.026 | 3.899 | 0.575 | 4.604 | 3.273 | — | — | — | |
| Segment-Aware Conditioning2026.01 | 0.0323 | 0.0323 | 3.988 | 0.532 | 4.766 | 3.336 | — | — | — |