RTFS-Net-12

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech6 results

Speech SeparationonLRS3
SDRi· 2023-09-29
17.6
best: 18.5 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189
Speech SeparationonLRS3
SI-SNRi· 2023-09-29
17.5
best: 18.3 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189
Speech SeparationonLRS2
SDRi· 2023-09-29
15.1
best: 16.6 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189
Speech SeparationonLRS2
SI-SNRi· 2023-09-29
14.9
best: 16.4 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189
Speech SeparationonVoxCeleb2
SDRi· 2023-09-29
13.6
best: 15.1 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189
Speech SeparationonVoxCeleb2
SI-SNRi· 2023-09-29
12.4
best: 14 (IIANet)
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation arXiv:2309.17189