Emotional Speech Synthesis on 27 fine-grained emotion tasks (Male)
4.05MOSEmoInstruct-TTS (Dual-Path)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| EmoInstruct-TTS (Dual-Path)mode=zero-shot2026.06 | 4.05 | 3.78 | 4.3 | |
| CosyVoice2mode=zero-shot2026.06 | 3.9 | 3.48 | 4.28 | |
| CosyVoice3mode=zero-shot2026.06 | 3.86 | 3.44 | 4.34 | |
| EmoInstruct-TTS (Text-Only)mode=zero-shot, ablation=w/o Emo2emb2026.06 | 3.78 | 3.26 | 4.18 | |
| EmoInstruct-TTS (Emo2embed-Only)mode=zero-shot, ablation=w/o Text Instruct2026.06 | 3.7 | 3.2 | 4.15 |