Speech Separation On Lrs3
評価指標
SDRi
SI-SNRi
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 | SDRi | SI-SNRi | Paper Title | Repository |
|---|---|---|---|---|
| RTFS-Net-6 | 17.1 | 16.9 | RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation | |
| RTFS-Net-4 | 15.6 | 15.5 | RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation | |
| CTCNet | - | 17.4 | An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits | |
| RTFS-Net-12 | 17.6 | 17.5 | RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation | |
| IIANet | 18.5 | 18.3 | IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation |
0 of 5 row(s) selected.