Speech Separation on WHAMR!

Metric: SI-SDRi (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	SI-SDRi▼	Extra Data	Paper	Date↕	Code
1	TF-Locoformer (M)	18.5	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
2	TF-Locoformer (S)	17.4	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
3	SepReformer-L + DM	17.1	No	Separate and Reconstruct: Asymmetric Encoder-Dec...	2024-06-10	Code
4	MossFormer2	17	No	-	-	Code
5	MossFormer (L) + DM	16.3	No	MossFormer: Pushing the Performance Limit of Mon...	2023-02-23	Code
6	TD-Conformer (XL) + DM	14.6	No	On Time Domain Conformer Models for Monaural Spe...	2023-10-09	Code
7	Improved Sudo rm -rf (U=36)	13.5	No	Compute and memory efficient universal sound sou...	2021-03-03	Code
8	TD-Conformer (L) + DM	13.4	No	On Time Domain Conformer Models for Monaural Spe...	2023-10-09	Code
9	Wavesplit	13.2	No	Wavesplit: End-to-End Speech Separation by Speak...	2020-02-20	-
10	DPTNET - SRSSN	12.3	No	Stepwise-Refining Speech Separation Network via ...	2021-10-10	-
11	DPRNN - SRSSN	12.3	No	Stepwise-Refining Speech Separation Network via ...	2021-10-10	-
12	VSUNOS	12.2	No	Voice Separation with an Unknown Number of Multi...	2020-02-29	Code
13	Sudo rm -rf (U=16)	12.1	No	Sudo rm -rf: Efficient Networks for Universal Au...	2020-07-14	Code
14	TD-Confomer (M) + DM	12	No	On Time Domain Conformer Models for Monaural Spe...	2023-10-09	Code
15	Deformable TCN + Dynamic Mixing	11.1	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code
16	TD-Confomer (S)	10.5	No	On Time Domain Conformer Models for Monaural Spe...	2023-10-09	Code
17	Deformable TCN + Shared Weights + Dynamic Mixing	10.1	No	Deformable Temporal Convolutional Networks for M...	2022-10-27	Code
18	Bi-LSTM-TASNET	9.2	No	WHAM!: Extending Speech Separation to Noisy Envi...	2019-07-02	Code

#1TF-Locoformer (M)SOTA
18.5
SI-SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#2TF-Locoformer (S)
17.4
SI-SDRi· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#3SepReformer-L + DMSOTA
17.1
SI-SDRi· 2024-06-10
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation Code
#4MossFormer2
17
SI-SDRi
No paperCode
#5MossFormer (L) + DMSOTA
16.3
SI-SDRi· 2023-02-23
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions Code
#6TD-Conformer (XL) + DM
14.6
SI-SDRi· 2023-10-09
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments Code
#7Improved Sudo rm -rf (U=36)SOTA
13.5
SI-SDRi· 2021-03-03
Compute and memory efficient universal sound source separation Code
#8TD-Conformer (L) + DM
13.4
SI-SDRi· 2023-10-09
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments Code
#9WavesplitSOTA
13.2
SI-SDRi· 2020-02-20
Wavesplit: End-to-End Speech Separation by Speaker Clustering
#10DPTNET - SRSSN
12.3
SI-SDRi· 2021-10-10
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
#11DPRNN - SRSSN
12.3
SI-SDRi· 2021-10-10
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
#12VSUNOS
12.2
SI-SDRi· 2020-02-29
Voice Separation with an Unknown Number of Multiple Speakers Code
#13Sudo rm -rf (U=16)
12.1
SI-SDRi· 2020-07-14
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation Code
#14TD-Confomer (M) + DM
12
SI-SDRi· 2023-10-09
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments Code
#15Deformable TCN + Dynamic Mixing
11.1
SI-SDRi· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code
#16TD-Confomer (S)
10.5
SI-SDRi· 2023-10-09
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments Code
#17Deformable TCN + Shared Weights + Dynamic Mixing
10.1
SI-SDRi· 2022-10-27
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation Code
#18Bi-LSTM-TASNETSOTA
9.2
SI-SDRi· 2019-07-02
WHAM!: Extending Speech Separation to Noisy Environments Code