Speech Separation on WSJ0-2mix

Metric: MACs (G) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	MACs (G)▼	Extra Data	Paper	Date↕	Code
1	SepReformer-L	155.5	No	Separate and Reconstruct: Asymmetric Encoder-Dec...	2024-06-10	Code
2	MossFormer (L) + DM	86.1	No	MossFormer: Pushing the Performance Limit of Mon...	2023-02-23	Code
3	SPGM + DM	77	No	SPGM: Prioritizing Local Features for enhanced s...	2023-09-22	Code
4	SPGM	77	No	SPGM: Prioritizing Local Features for enhanced s...	2023-09-22	Code
5	Deformable TCN + Dynamic Mixing	3.7	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code
6	Deformable TCN + Shared Weights + Dynamic Mixing	3.7	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code

#1SepReformer-LSOTA
155.5
MACs (G)· 2024-06-10
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation Code
#2MossFormer (L) + DMSOTA
86.1
MACs (G)· 2023-02-23
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions Code
#3SPGM + DM
77
MACs (G)· 2023-09-22
SPGM: Prioritizing Local Features for enhanced speech separation performance Code
#4SPGM
77
MACs (G)· 2023-09-22
SPGM: Prioritizing Local Features for enhanced speech separation performance Code
#5Deformable TCN + Dynamic MixingSOTA
3.7
MACs (G)· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code
#6Deformable TCN + Shared Weights + Dynamic Mixing
3.7
MACs (G)· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code