Speech Expressiveness Appropriateness Assessment on CEAEval 1.0 (test)
0.72LCCCEAEval-M
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CEAEval-MCoT=w, CTS=152026.05 | 0.72 | 70.8 | |
| CEAEval-MCoT=w, CTS=102026.05 | 0.71 | 70.12 | |
| CEAEval-MCoT=w, CTS=52026.05 | 0.69 | 68.47 | |
| CEAEval-MCoT=w/o, CTS=102026.05 | 0.61 | 64.11 | |
| CEAEval-MCoT=w/o, CTS=152026.05 | 0.61 | 65.47 | |
| CEAEval-MCoT=w, CTS=02026.05 | 0.61 | 64.33 | |
| CEAEval-MCoT=w/o, CTS=52026.05 | 0.58 | 62 | |
| CEAEval-MCoT=w/o, CTS=02026.05 | 0.54 | 59.96 | |
| Voxtral-MiniCoT=w/o, CTS=52026.05 | 0.33 | 31.11 | |
| Qwen3-OmniCoT=w, CTS=52026.05 | 0.3 | 29.49 | |
| Qwen3-OmniCoT=w, CTS=102026.05 | 0.29 | 32.74 | |
| Qwen3-OmniCoT=w/o, CTS=152026.05 | 0.28 | 33.55 | |
| Phi-4-MMCoT=w/o, CTS=52026.05 | 0.27 | 33.22 | |
| Qwen3-OmniCoT=w/o, CTS=52026.05 | 0.27 | 34.85 | |
| Qwen3-OmniCoT=w/o, CTS=102026.05 | 0.25 | 35.18 | |
| MidashenglmCoT=w/o, CTS=52026.05 | 0.24 | 28.99 | |
| Voxtral-MiniCoT=w/o, CTS=102026.05 | 0.23 | 31.27 | |
| GPT-4o-AudioCoT=w, CTS=152026.05 | 0.22 | 27.41 | |
| Voxtral-MiniCoT=w/o, CTS=152026.05 | 0.22 | 30.94 | |
| Qwen3-OmniCoT=w, CTS=152026.05 | 0.22 | 30.13 | |
| Gemma-3nCoT=w/o, CTS=52026.05 | 0.21 | 40.07 | |
| Qwen3-OmniCoT=w/o, CTS=02026.05 | 0.21 | 35.34 | |
| Qwen3-OmniCoT=w, CTS=02026.05 | 0.21 | 24.42 | |
| Voxtral-MiniCoT=w/o, CTS=02026.05 | 0.2 | 32.74 | |
| Kimi-AudioCoT=w/o, CTS=102026.05 | 0.19 | 33.71 | |
| MidashenglmCoT=w, CTS=52026.05 | 0.19 | 28.83 | |
| MidashenglmCoT=w, CTS=102026.05 | 0.19 | 34.04 | |
| GPT-4o-AudioCoT=w, CTS=102026.05 | 0.19 | 26.71 | |
| Phi-4-MMCoT=w/o, CTS=102026.05 | 0.18 | 25.2 | |
| GPT-4o-AudioCoT=w, CTS=52026.05 | 0.18 | 22.76 | |
| Kimi-AudioCoT=w/o, CTS=52026.05 | 0.17 | 36.32 | |
| Step-Audio-R1CoT=w, CTS=52026.05 | 0.17 | 25.73 | |
| MidashenglmCoT=w/o, CTS=152026.05 | 0.17 | 29.8 | |
| Gemini-3-ProCoT=w, CTS=52026.05 | 0.17 | 20.43 | |
| Qwen2.5-OmniCoT=w/o, CTS=52026.05 | 0.16 | 27.85 | |
| Step-Audio-R1CoT=w/o, CTS=02026.05 | 0.16 | 28.83 | |
| Step-Audio-R1CoT=w/o, CTS=102026.05 | 0.16 | 26.22 | |
| MidashenglmCoT=w/o, CTS=102026.05 | 0.16 | 32.9 | |
| Gemini-3-ProCoT=w/o, CTS=102026.05 | 0.16 | 26.23 | |
| Qwen2.5-OmniCoT=w/o, CTS=102026.05 | 0.15 | 27.69 | |
| Gemma-3nCoT=w/o, CTS=02026.05 | 0.15 | 30.78 | |
| Voxtral-MiniCoT=w, CTS=102026.05 | 0.15 | 31.76 | |
| Qwen2.5-OmniCoT=w, CTS=52026.05 | 0.14 | 31.43 | |
| Gemma-3nCoT=w, CTS=02026.05 | 0.14 | 31.27 | |
| Gemini-3-ProCoT=w/o, CTS=52026.05 | 0.14 | 27.69 | |
| Gemini-3-ProCoT=w, CTS=102026.05 | 0.14 | 18.73 | |
| Kimi-AudioCoT=w/o, CTS=152026.05 | 0.13 | 31.6 | |
| GPT-4o-AudioCoT=w/o, CTS=102026.05 | 0.13 | 31.66 | |
| Step-Audio-R1CoT=w/o, CTS=52026.05 | 0.12 | 27.69 | |
| Gemini-3-ProCoT=w, CTS=152026.05 | 0.12 | 21.17 | |
| Qwen2.5-OmniCoT=w, CTS=102026.05 | 0.11 | 30.94 | |
| Step-Audio-R1CoT=w/o, CTS=152026.05 | 0.11 | 27.2 | |
| GPT-4o-AudioCoT=w, CTS=02026.05 | 0.11 | 23.16 | |
| Gemini-3-ProCoT=w/o, CTS=02026.05 | 0.11 | 29.41 | |
| Phi-4-MMCoT=w/o, CTS=152026.05 | 0.1 | 32.08 | |
| Gemma-3nCoT=w/o, CTS=102026.05 | 0.1 | 29.15 | |
| Gemma-3nCoT=w, CTS=52026.05 | 0.1 | 34.04 | |
| Gemini-3-ProCoT=w/o, CTS=152026.05 | 0.1 | 26.41 | |
| Qwen2.5-OmniCoT=w/o, CTS=02026.05 | 0.09 | 28.01 | |
| Qwen2.5-OmniCoT=w, CTS=152026.05 | 0.09 | 28.83 | |
| MidashenglmCoT=w/o, CTS=02026.05 | 0.09 | 22.8 | |
| MidashenglmCoT=w, CTS=152026.05 | 0.09 | 35.71 | |
| GPT-4o-AudioCoT=w/o, CTS=52026.05 | 0.09 | 31.82 | |
| Gemini-3-ProCoT=w, CTS=02026.05 | 0.09 | 22.41 | |
| Step-Audio-R1CoT=w, CTS=02026.05 | 0.08 | 22.8 | |
| GPT-4o-AudioCoT=w/o, CTS=02026.05 | 0.08 | 29.99 | |
| Qwen2.5-OmniCoT=w/o, CTS=152026.05 | 0.07 | 28.99 | |
| Phi-4-MMCoT=w, CTS=52026.05 | 0.07 | 34.69 | |
| Gemma-3nCoT=w, CTS=152026.05 | 0.07 | 32.84 | |
| Step-Audio-R1CoT=w, CTS=152026.05 | 0.07 | 24.43 | |
| Kimi-AudioCoT=w, CTS=52026.05 | 0.06 | 29.48 | |
| Phi-4-MMCoT=w, CTS=102026.05 | 0.06 | 30.78 | |
| Phi-4-MMCoT=w, CTS=152026.05 | 0.06 | 32.9 | |
| Gemma-3nCoT=w/o, CTS=152026.05 | 0.06 | 28.34 | |
| GPT-4o-AudioCoT=w/o, CTS=152026.05 | 0.06 | 32.73 | |
| Voxtral-MiniCoT=w, CTS=152026.05 | 0.06 | 29.8 | |
| Kimi-AudioCoT=w, CTS=02026.05 | 0.04 | 30.13 | |
| Kimi-AudioCoT=w, CTS=102026.05 | 0.04 | 26.22 | |
| Gemma-3nCoT=w, CTS=102026.05 | 0.04 | 34.85 | |
| Voxtral-MiniCoT=w, CTS=02026.05 | 0.04 | 33.39 | |
| Qwen2.5-OmniCoT=w, CTS=02026.05 | 0.03 | 28.11 | |
| Kimi-AudioCoT=w, CTS=152026.05 | 0.03 | 26.71 | |
| Step-Audio-R1CoT=w, CTS=102026.05 | 0.03 | 24.27 | |
| Voxtral-MiniCoT=w, CTS=52026.05 | 0.02 | 32.57 | |
| Phi-4-MMCoT=w, CTS=02026.05 | 0 | 32.74 | |
| Kimi-AudioCoT=w/o, CTS=02026.05 | -0.01 | 35.67 | |
| Phi-4-MMCoT=w/o, CTS=02026.05 | -0.01 | 33.39 | |
| MidashenglmCoT=w, CTS=02026.05 | -0.04 | 21.82 |