Role-Play Text-to-Speech on Role-Play TTS Curated Evaluation Set Without Audio History
1.625CEROur Proposed
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Our Proposed2026.01 | 1.625 | 0.97 | -4.687 | |
| MiMo-Audio-7B-Instructresynthesized_via_Step-Audio-2_tokenizer=true2026.01 | 11.609 | 9.83 | -4.745 | |
| Step-Audio-2-mini2026.01 | 12.007 | 10.927 | -4.823 | |
| GPT-Audioresynthesized_via_Step-Audio-2_tokenizer=true2026.01 | 44.679 | 43.634 | -4.836 |