Speaker Specific Lip To Speech Synthesis On 3
評価指標
ESTOI
PESQ
STOI
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | ESTOI | PESQ | STOI | Paper Title | Repository |
|---|---|---|---|---|---|
| Visual Voice Memory | 0.304 | 1.362 | 0.463 | Speech Reconstruction with Reminiscent Sound via Visual Voice Memory | - |
| Lip2Wav | 0.22 | 1.367 | 0.369 | Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis |
0 of 2 row(s) selected.