Emotion Generation on GenEmo (test)
48.13ScoreGLM-4-VOICE
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-4-VOICEGroup=Group B2026.07 | 48.13 | |
| SPEECHCOMBINEGroup=Group B2026.07 | 45.42 | |
| FUN-AUDIO-CHATGroup=Group B2026.07 | 39.3 | |
| OSUM-ECHATGroup=Group B2026.07 | 36.01 | |
| GPT-4O-AUDIOGroup=Topline2026.07 | 33.46 | |
| STEP-AUDIO2-MINIGroup=Group B2026.07 | 31.35 | |
| KIMI-AUDIOGroup=Group B2026.07 | 28.01 | |
| CONT. PRE-TRAINGroup=Group A2026.07 | 24.23 | |
| CONT. PRE-TRAIN + SFTGroup=Group A2026.07 | 24.23 | |
| STEP-AUDIO2-MINI-THINKGroup=Group B2026.07 | 23.73 | |
| QWEN-2.5-OMNIGroup=Group B2026.07 | 13.54 | |
| ASR + TEXT LLMGroup=Group A, Generation engine=Kokoro text-to-speech2026.07 | 5.06 |