Mixed-emotion Text-to-Speech on CREMA-D (in-distribution)
0.795Embedding Similarity (E-SIM)
CoCoEmo
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.02 | 0.795 | 31.5 | 0.297 | 0.755 | 0.845 | 0.91 | 3.66 | |
2026.02 | 0.79 | 33.5 | 0.319 | 0.76 | 0.846 | 0.2 | 3 | |
2026.02 | 0.782 | 14 | 0.24 | 0.734 | 0.863 | 5.81 | 4.13 | |
2026.02 | 0.78 | 29.1 | 0.225 | 0.728 | 0.849 | 0.27 | 3.38 | |
2026.02 | 0.779 | 14.9 | 0.209 | 0.724 | 0.87 | 0.78 | 3.96 | |
2026.02 | 0.777 | 26.6 | 0.207 | 0.726 | 0.852 | 0.53 | 3.42 | |
2026.02 | 0.774 | 27.8 | 0.399 | 0.789 | 0.836 | 5.89 | 4.16 | |
2026.02 | 0.77 | 24.7 | 0.324 | 0.76 | 0.845 | 5.85 | 4.66 | |
2026.02 | 0.767 | 16.5 | 0.236 | 0.731 | 0.85 | 5.74 | 4.05 | |
2026.02 | 0.767 | 9 | 0.072 | 0.681 | 0.864 | 5.83 | 3.95 | |
2026.02 | 0.762 | 16.9 | 0.104 | 0.688 | 0.851 | 0.06 | 3.36 | |
2026.02 | 0.762 | 10 | 0.166 | 0.709 | 0.872 | 1.01 | 4.25 | |
2026.02 | 0.761 | 20 | 0.111 | 0.694 | 0.853 | 0.22 | 4.11 | |
2026.02 | 0.751 | 3.7 | - | - | 0.864 | 5.72 | 3.82 | |
2026.02 | 0.743 | 6.5 | - | - | 0.871 | 1.07 | 4.11 |