Emotion-intensity Speech Synthesis on ESD & CNCED (Male)
4.25MOSEmoInstruct-TTS (Dual-Path)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| EmoInstruct-TTS (Dual-Path)Evaluation mode=zero-shot, Variant=Dual-Path2026.06 | 4.25 | 4.1 | 4.48 | |
| CosyVoice2Evaluation mode=zero-shot2026.06 | 4.14 | 3.8 | 4.5 | |
| EmoInstruct-TTS -w/o Text Instruct (Emo2emb-Only)Evaluation mode=zero-shot, Variant=Emo2emb-Only2026.06 | 4.09 | 3.86 | 4.44 | |
| CosyVoice3Evaluation mode=zero-shot2026.06 | 4.08 | 3.92 | 4.55 | |
| EmoInstruct-TTS -w/o Emo2emb (Text-Only)Evaluation mode=zero-shot, Variant=Text-Only2026.06 | 4.05 | 3.7 | 4.42 |