Speaker Specific Lip To Speech Synthesis On 7
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 |
|---|---|---|---|---|---|
| Lip2Wav | 0.284 | 1.3 | 0.416 | Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis | |
| Visual Voice Memory | 0.429 | 1.529 | 0.566 | Speech Reconstruction with Reminiscent Sound via Visual Voice Memory |
0 of 2 row(s) selected.