List your company

Emotional Speech Synthesis Evaluation on Fine-Grained Non-Verbal Expression Data

3.67nMOS (Happy)Only Verbal
3.17083.30043.433.5596May 25, 2026

Evaluation results

MethodLinks
Only VerbalNon-Verbal Cues Granularity=Only Verbal2026.053.673.783.693.833.613.743.193.89
Fine-Grained NV Emotional TTSNon-Verbal Cues Granularity=Fine-Grained NV2026.053.434.213.674.253.344.063.184.28
Coarse-grained NVNon-Verbal Cues Granularity=Coarse-grained NV2026.053.193.853.734.15————