Speech Enhancement On Demand

评估指标

PESQ (wb)

Para. (M)

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
PESQetarian	3.82	30	The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement	-
Mamba-SEUNet L (+PCS)	3.73	6.28	Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement
Schrödinger bridge (PESQ loss)	3.70	-	Investigating Training Objectives for Generative Speech Enhancement
SEMamba (+PCS)	3.69	2.25	An Investigation of Incorporating Mamba for Speech Enhancement
ZipEnhancer (S, lamba_6 = 0)	3.63	2.04	-	-
ZipEnhancer (S, lamba_6 = 0.2)	3.61	2.04	-	-
PrimeK-Net	3.61	1.41	PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement
MP-SENet	3.60	2.26	Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
PCS_CS_WAVLM	3.54	-	-	-
xLSTM-SENet2	3.53	2.27	xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
SCP-CMGAN	3.52	-	SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks	-
D2Former	3.43	0.86	Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses
CMGAN	3.41	-	CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
PCS	3.35	-	Perceptual Contrast Stretching on Target Feature for Speech Enhancement
aTENNuate	3.27	-	aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio	-
D²Net	3.27	-	D²Net: A Denoising and Dereverberation Network Based on Two-branch Encoder and Dual-path Transformer	-
Centaurus (0.51M)	3.25	-	Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions	-
MetricGAN-OKD	3.24	1.89	MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement	-
MANNER	3.21	-	MANNER: Multi-view Attention Network for Noise Erasure
BSSE-SE	3.20	-	Boosting Self-Supervised Embeddings for Speech Enhancement

0 of 40 row(s) selected.