ML Research Wiki / Benchmarks / Speech Separation / LRS2

LRS2

Speech Separation Benchmark

Performance Over Time

📊 Showing 8 results | 📏 Metric: SI-SNRi

Top Performing Models

Rank Model Paper SI-SNRi Date Code
1 IIANet IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation 16.40 2023-08-16 📦 JusperLee/IIANet
2 TDFNet-large TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion 15.80 2024-01-25 📦 spkgyk/TDFNet
3 TDFNet (MHSA + Shared) TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion 15.00 2024-01-25 📦 spkgyk/TDFNet
4 RTFS-Net-12 RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation 14.90 2023-09-29 📦 spkgyk/RTFS-Net
5 RTFS-Net-6 RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation 14.60 2023-09-29 📦 spkgyk/RTFS-Net
6 CTCNet An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits 14.30 2022-12-21 📦 jusperlee/lrs3-for-speech-separation 📦 jusperlee/ctcnet
7 RTFS-Net-4 RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation 14.10 2023-09-29 📦 spkgyk/RTFS-Net
8 TDFNet-small TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion 13.60 2024-01-25 📦 spkgyk/TDFNet

All Papers (8)

JusperLee/IIANet
spkgyk/TDFNet
spkgyk/TDFNet
spkgyk/RTFS-Net
spkgyk/RTFS-Net
jusperlee/lrs3-for-speech-separation jusperlee/ctcnet
spkgyk/RTFS-Net
spkgyk/TDFNet