Audio-Visual Speaker Separation on VoxCeleb2 2Mix (test)
12.4SI-SNRiRTFS-Net-12
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RTFS-Net-12Params (M)=0.7, MACS (G)=56.4, Time (ms)=109.92023.09 | 12.4 | 13.6 | 3 | |
| CTCNetParams (M)=7.0, MACS (G)=167.2, Time (ms)=122.72023.09 | 11.9 | 13.1 | 3 | |
| RTFS-Net-6Params (M)=0.7, MACS (G)=30.5, Time (ms)=64.72023.09 | 11.8 | 12.8 | 2.97 | |
| RTFS-Net-4Params (M)=0.7, MACS (G)=21.9, Time (ms)=57.82023.09 | 11.5 | 12.4 | 2.94 | |
| AVLITParams (M)=5.8, MACS (G)=36.4, Time (ms)=53.42023.09 | 9.4 | 9.9 | 2.23 | |
| VisualVoiceParams (M)=77.8, Time (ms)=130.22023.09 | 9.3 | 10.2 | — | |
| AV-ConvTasnetParams (M)=16.5, Time (ms)=60.32023.09 | 9.2 | 9.8 | — |