Speech Enhancement on Deep Noise Suppression (DNS) Challenge

Metric: Number of parameters (M) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Number of parameters (M)▼	Extra Data	Paper	Date↕	Code
1	TF-Locoformer (M)	15	No	TF-Locoformer: Transformer with Local Modeling b...	2024-08-06	Code
2	ZipEnhancer (M)	11.34	No	-	-	-
3	MambAttention	2.33	No	MambAttention: Mamba with Multi-Head Attention f...	2025-07-01	Code
4	xLSTM-SENet	2.2	No	MambAttention: Mamba with Multi-Head Attention f...	2025-07-01	Code
5	ZipEnhancer (S)	2.04	No	-	-	-

#1TF-Locoformer (M)SOTA
15
Number of parameters (M)· 2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement Code
#2ZipEnhancer (M)
11.34
Number of parameters (M)
No paper
#3MambAttention
2.33
Number of parameters (M)· 2025-07-01
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement Code
#4xLSTM-SENet
2.2
Number of parameters (M)· 2025-07-01
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement Code
#5ZipEnhancer (S)
2.04
Number of parameters (M)
No paper