Role-Play Text-to-Speech on Role-Play TTS Curated Evaluation Set (With Audio History)
1.13CEROur Proposed
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Our Proposed2026.01 | 1.13 | 0.511 | -4.636 | |
| Step-Audio-2-mini2026.01 | 3.276 | 2.031 | -4.829 | |
| MiMo-Audio-7B-Instructresynthesized_via_Step-Audio-2_tokenizer=true2026.01 | 10.605 | 8.519 | -4.753 | |
| GPT-Audioresynthesized_via_Step-Audio-2_tokenizer=true2026.01 | 11.974 | 10.51 | -4.849 |