HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Speech Enhancement On Demand

Metrics

PESQ (wb)
Para. (M)

Results

Performance results of various models on this benchmark

Paper TitleRepository
PESQetarian3.8230The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement-
Mamba-SEUNet L (+PCS)3.736.28Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement
Schrödinger bridge (PESQ loss)3.70-Investigating Training Objectives for Generative Speech Enhancement
SEMamba (+PCS)3.692.25An Investigation of Incorporating Mamba for Speech Enhancement
ZipEnhancer (S, lamba_6 = 0)3.632.04--
ZipEnhancer (S, lamba_6 = 0.2)3.612.04--
PrimeK-Net3.611.41PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement
MP-SENet3.602.26Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
PCS_CS_WAVLM3.54---
xLSTM-SENet23.532.27xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
SCP-CMGAN3.52-SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks-
D2Former3.430.86Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses
CMGAN3.41-CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
PCS3.35-Perceptual Contrast Stretching on Target Feature for Speech Enhancement
aTENNuate3.27-aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio-
D²Net3.27-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-OKD3.241.89MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement-
MANNER3.21-MANNER: Multi-view Attention Network for Noise Erasure
BSSE-SE3.20-Boosting Self-Supervised Embeddings for Speech Enhancement
0 of 40 row(s) selected.
Speech Enhancement On Demand | SOTA | HyperAI