Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Emotional Speech Synthesis on 27 fine-grained emotion tasks (Female)
Loading...
4.12
MOS
EmoInstruct-TTS (Dual-Path)
3.8392
3.9121
3.985
4.0579
Jun 8, 2026
MOS
ESMOS
SSMOS
Updated 1mo ago
Evaluation Results
Method
Method
Links
MOS
ESMOS
SSMOS
EmoInstruct-TTS (Dual-Path)
mode=zero-shot
2026.06
4.12
3.92
4.31
CosyVoice2
mode=zero-shot
2026.06
3.98
3.55
4.3
CosyVoice3
mode=zero-shot
2026.06
3.92
3.5
4.36
EmoInstruct-TTS (Emo2embed-Only)
mode=zero-shot, ablati...
2026.06
3.88
3.48
4.24
EmoInstruct-TTS (Text-Only)
mode=zero-shot, ablati...
2026.06
3.85
3.32
4.22
Feedback
Search any
task
Search any
task