Speech Separation on WSJ0-2mix

Metric: SDRi (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	SDRi▼	Extra Data	Paper	Date↕	Code
1	TF-Locoformer (L) + DM	25.2	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
2	SepReformer-L	25.2	No	Separate and Reconstruct: Asymmetric Encoder-Dec...	2024-06-10	Code
3	TF-Locoformer (M) + DM	24.7	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
4	TF-Locoformer (L)	24.3	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
5	TF-Locoformer (M)	23.8	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
6	TF-Locoformer (S) + DM	23	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
7	SepMamba + DM (M)	22.9	No	SepMamba: State-space models for speaker separat...	2024-10-28	Code
8	SepFormer	22.4	No	Attention is All You Need in Speech Separation	2020-10-25	Code
9	Wavesplit v2	22.3	No	Wavesplit: End-to-End Speech Separation by Speak...	2020-02-20	-
10	TF-Locoformer (S)	22.1	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
11	DPTNet (Libri1Mix speech enhancement pre-trained)	21.5	Yes	Stabilizing Label Assignment for Speech Separati...	2020-10-29	Code
12	SepMamba + DM (S)	21.4	No	SepMamba: State-space models for speaker separat...	2024-10-28	Code
13	Deformable TCN + Dynamic Mixing	17.4	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code
14	Deformable TCN + Shared Weights + Dynamic Mixing	16.3	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code
15	Conv-TasNet	15.6	No	Conv-TasNet: Surpassing Ideal Time-Frequency Mag...	2018-09-20	Code

#1TF-Locoformer (L) + DM
25.2
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#2SepReformer-LSOTA
25.2
SDRi· 2024-06-10
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation Code
#3TF-Locoformer (M) + DM
24.7
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#4TF-Locoformer (L)
24.3
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#5TF-Locoformer (M)
23.8
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#6TF-Locoformer (S) + DM
23
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#7SepMamba + DM (M)
22.9
SDRi· 2024-10-28
SepMamba: State-space models for speaker separation using Mamba Code
#8SepFormerSOTA
22.4
SDRi· 2020-10-25
Attention is All You Need in Speech Separation Code
#9Wavesplit v2SOTA
22.3
SDRi· 2020-02-20
Wavesplit: End-to-End Speech Separation by Speaker Clustering
#10TF-Locoformer (S)
22.1
SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#11DPTNet (Libri1Mix speech enhancement pre-trained)
21.5
SDRi· Extra Data· 2020-10-29
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training Code
#12SepMamba + DM (S)
21.4
SDRi· 2024-10-28
SepMamba: State-space models for speaker separation using Mamba Code
#13Deformable TCN + Dynamic Mixing
17.4
SDRi· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code
#14Deformable TCN + Shared Weights + Dynamic Mixing
16.3
SDRi· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code
#15Conv-TasNetSOTA
15.6
SDRi· 2018-09-20
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Code