Home Console Docs News Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Speech Separation On Wsj0 3Mix

Metrics

SI-SDRi

Results

Performance results of various models on this benchmark

		Paper Title	Repository
SepTDA	23.7	Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor	-
MossFormer2	22.2	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
MossFormer (L) + DM	21.2	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
Separate And Diffuse	20.9	Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation	-
MossFormer (M) + DM	20.8	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SepIt	20.1	SepIt: Approaching a Single Channel Speech Separation Bound	-
SepFormer	19.5	Attention is All You Need in Speech Separation
Sandglasset	17.1	Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
Gated DualPathRNN	16.85	Voice Separation with an Unknown Number of Multiple Speakers

0 of 9 row(s) selected.

Speech Separation On Wsj0 3Mix | SOTA | HyperAI