Speech Separation On Wsj0 2Mix

评估指标

Number of parameters (M)

SDRi

SI-SDRi

评测结果

各个模型在此基准测试上的表现结果

				Paper Title	Repository
SepReformer-L	59.4	25.2	25.1	Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
TF-Locoformer (L) + DM	22.5	25.2	25.1	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (M) + DM	15.0	24.7	24.6	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (L)	22.5	24.3	24.2	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
MossFormer2 (L)	55.7	-	24.1	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
SepTDA (L=12)	-	-	24.0	Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor	-
Separate And Diffuse	-	-	23.9	Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation	-
TF-Locoformer (M)	15.0	23.8	23.6	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (S) + DM	5.0	23	22.8	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
MossFormer (L) + DM	42.1	-	22.8	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SPGM + DM	26.2	-	22.7	SPGM: Prioritizing Local Features for enhanced speech separation performance
MossFormer (M) + DM	-	-	22.5	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SepIt	-	-	22.4	SepIt: Approaching a Single Channel Speech Separation Bound	-
SepFormer	-	22.4	22.3	Attention is All You Need in Speech Separation
Wavesplit v2	-	22.3	22.2	Wavesplit: End-to-End Speech Separation by Speaker Clustering	-
SPGM	26.2	-	22.1	SPGM: Prioritizing Local Features for enhanced speech separation performance
TF-Locoformer (S)	5.0	22.1	22	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
DPTNet (Libri1Mix speech enhancement pre-trained)	-	21.5	21.3	Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
TD-Conformer (XL) + DM	-	-	21.2	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Sandglasset	-	-	21.0	Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation

0 of 38 row(s) selected.