SOTAVerified

Speech Enhancement

Speech Enhancement is a signal processing task that involves improving the quality of speech signals captured under noisy or degraded conditions. The goal of speech enhancement is to make speech signals clearer, more intelligible, and more pleasant to listen to, which can be used for various applications such as voice recognition, teleconferencing, and hearing aids. A representative Github project with online demo : ClearerVoice-Studio.

( Image credit: A Fully Convolutional Neural Network For Speech Enhancement )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 982 papers

TitleStatusHype
FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow MatchingCode2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPTCode2
Mamba-SEUNet: Mamba UNet for Monaural Speech EnhancementCode2
Real Time Speech Enhancement in the Waveform DomainCode2
UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture SearchCode2
Integrating Uncertainty into Neural Network-based Speech EnhancementCode1
FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio ProcessingCode1
Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative ConditionsCode1
Insights Into Deep Non-linear Filters for Improved Multi-channel Speech EnhancementCode1
Interactive Feature Fusion for End-to-End Noise-Robust Speech RecognitionCode1
Instantaneous PSD Estimation for Speech Enhancement based on Generalized Principal ComponentsCode1
Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech EnhancementCode1
AnCoGen: Analysis, Control and Generation of Speech with a Masked AutoencoderCode1
Explainable DNN-based Beamformer with PostfilterCode1
Improving Speech Enhancement through Fine-Grained Speech CharacteristicsCode1
Inference and Denoise: Causal Inference-based Neural Speech EnhancementCode1
INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video ConferencingCode1
EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy EnvironmentsCode1
Improved Lite Audio-Visual Speech EnhancementCode1
Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementCode1
DNN-based mask estimation for distributed speech enhancement in spatially unconstrained microphone arraysCode1
Dual-Path Style Learning for End-to-End Noise-Robust Speech RecognitionCode1
Improving GANs for Speech EnhancementCode1
A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint ModelsCode1
Disentanglement in a GAN for Unconditional Speech SynthesisCode1
Diffusion-based Generative Speech Source SeparationCode1
DeFTAN-II: Efficient Multichannel Speech Enhancement with Subgroup ProcessingCode1
Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found DataCode1
Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance MatricesCode1
Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech EnhancementCode1
Investigating the Design Space of Diffusion Models for Speech EnhancementCode1
A Differentiable Perceptual Audio Metric Learned from Just Noticeable DifferencesCode1
A Mask Free Neural Network for Monaural Speech EnhancementCode1
Hold Me Tight: Stable Encoder-Decoder Design for Speech EnhancementCode1
D4AM: A General Denoising Framework for Downstream Acoustic ModelsCode1
HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial NetworksCode1
Continual self-training with bootstrapped remixing for speech enhancementCode1
High Fidelity Speech Enhancement with Band-split RNNCode1
A Refining Underlying Information Framework for Monaural Speech EnhancementCode1
dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal ProcessingCode1
Complex-valued Spatial Autoencoders for Multichannel Speech EnhancementCode1
A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband SpeechCode1
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and SeparationCode1
Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain FeaturesCode1
A Causal U-net based Neural Beamforming Network for Real-Time Multi-Channel Speech EnhancementCode1
DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech EnhancementCode1
A Modulation-Domain Loss for Neural-Network-based Real-time Speech EnhancementCode1
Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic ModelsCode1
A light-weight full-band speech enhancement modelCode1
A Deep Learning Loss Function based on Auditory Power Compression for Speech EnhancementCode1
Show:102550
← PrevPage 2 of 20Next →
All datasetsVoiceBank + DEMANDDeep Noise Suppression (DNS) ChallengeCHiME-3EARS-WHAMEasyComDNS ChallengeVB-DemandExWHAMR!WSJ0 + DEMAND + RNNoiseRealMANVoiceBank+DEMANDDEMAND

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ROSE-CD(PESQ)PESQ (wb)3.99—Unverified
2PESQetarianPESQ (wb)3.82—Unverified
3Mamba-SEUNet L (+PCS)PESQ (wb)3.73—Unverified
4Schrödinger bridge (PESQ loss)PESQ (wb)3.7—Unverified
5SEMamba (+PCS)PESQ (wb)3.69—Unverified
6ZipEnhancer (S, \lamba_6 = 0)PESQ (wb)3.63—Unverified
7PrimeK-NetPESQ (wb)3.61—Unverified
8ZipEnhancer (S, \lamba_6 = 0.2)PESQ (wb)3.61—Unverified
9MP-SENetPESQ (wb)3.6—Unverified
10PCS_CS_WAVLMPESQ (wb)3.54—Unverified
#ModelMetricClaimedVerifiedStatus
1BSRNN-S + MGDSI-SDR-WB21.4—Unverified
2DTLNSI-SDR-WB16.34—Unverified
3Non-Real-Time MultiScale+SI-SDR-WB16.22—Unverified
4ZipEnhancer (M)PESQ-WB3.81—Unverified
5TF-Locoformer (M)PESQ-WB3.72—Unverified
6ZipEnhancer (S)PESQ-WB3.69—Unverified
7MambAttentionPESQ-WB3.67—Unverified
8MP-SENetPESQ-WB3.62—Unverified
9xLSTM-SENetPESQ-WB3.59—Unverified
10BSRNN-S + MRSDPESQ-WB3.53—Unverified
#ModelMetricClaimedVerifiedStatus
1Inter-Channel Conv-TasNetSDR19.67—Unverified
2CA Dense U-Net (Complex)SDR18.64—Unverified
3Dense U-Net (Complex)SDR18.4—Unverified
4Dense U-Net (Real)SDR16.86—Unverified
5U-Net (Real)SDR15.97—Unverified
6Noisy/unprocessedSDR6.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Schrödinger Bridge (PESQ loss)PESQ-WB3.09—Unverified
2SGMSE+PESQ-WB2.5—Unverified
3Demucs v4PESQ-WB2.37—Unverified
4Schrödinger BridgePESQ-WB2.33—Unverified
5Conv-TasNetPESQ-WB2.31—Unverified
6CDiffuSEPESQ-WB1.6—Unverified
#ModelMetricClaimedVerifiedStatus
1ReVISE (ch2)Audio Quality MOS4.19—Unverified
2ReVISE (bf)Audio Quality MOS4.11—Unverified
3Demucs (ch2)Audio Quality MOS2.95—Unverified
4Demucs (bf)Audio Quality MOS2.39—Unverified
5MaxDI (Baseline)PESQ1.17—Unverified
6DAJA (MVDR,HMA,1000) (Overlapped Speech)SDR-4.76—Unverified
#ModelMetricClaimedVerifiedStatus
1ZipEnhancer (M)PESQ-NB4.08—Unverified
2DCCRN-MCPESQ-NB3.21—Unverified
3DCCRN-MPESQ-NB3.15—Unverified
4DCCRNPESQ-NB3.04—Unverified
5RNN-ModulationPESQ-WB2.75—Unverified
#ModelMetricClaimedVerifiedStatus
1MambAttentionESTOI0.8—Unverified
2SEMambaESTOI0.8—Unverified
3xLSTM-SENetESTOI0.8—Unverified
4MP-SENetESTOI0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1SepFormerPESQ2.84—Unverified
2DTLNPESQ2.23—Unverified
3UnprocessedPESQ1.83—Unverified
4Non-Real-Time MultiScale+PESQ1.52—Unverified
#ModelMetricClaimedVerifiedStatus
1DCUNet-MCPESQ-NB3.44—Unverified
2DCCRN-MPESQ-NB3.28—Unverified
3DCUNetPESQ-NB3.25—Unverified
#ModelMetricClaimedVerifiedStatus
1CleanMel-L-mapDNSMOS3.82—Unverified
2SpatialNetDNSMOS BAK3.43—Unverified
#ModelMetricClaimedVerifiedStatus
1rose_cd(PESQ )PESQ3.99—Unverified
2ROSE-CDPESQ3.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Wave-U-NetCBAK3.24—Unverified
#ModelMetricClaimedVerifiedStatus
1Audio-Visual concat-refPESQ2.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SE-MelGANAudio Quality MOS3.1—Unverified
#ModelMetricClaimedVerifiedStatus
1DeFT-ANPESQ3.01—Unverified
#ModelMetricClaimedVerifiedStatus
1Audio-Visual concat-refPESQ3.03—Unverified
#ModelMetricClaimedVerifiedStatus
1SepFormerPESQ3.07—Unverified