Speech Separation On Voxceleb2

SDRi

SI-SNRi

Results

Performance results of various models on this benchmark

			Paper Title
IIANet	15.1	14.0	IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
RTFS-Net-12	13.6	12.4	RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
CTCNet	-	11.9	An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits
RTFS-Net-6	12.8	11.8	RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
RTFS-Net-4	12.4	11.5	RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

0 of 5 row(s) selected.