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 1–10 of 982 papers

TitleStatusHype
Autoregressive Speech Enhancement via Acoustic Tokens—0
P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge—0
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis—0
Robust One-step Speech Enhancement via Consistency DistillationCode1
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementCode2
Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement—0
EDNet: A Distortion-Agnostic Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training—0
A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments—0
Efficient Speech Enhancement via Embeddings from Pre-trained Generative AudioencodersCode2
Exploring Length Generalization For Transformer-based Speech Enhancement—0
Show:102550
← PrevPage 1 of 99Next →
All datasetsVoiceBank + DEMANDDeep Noise Suppression (DNS) ChallengeCHiME-3EARS-WHAMEasyComDNS ChallengeVB-DemandExWHAMR!WSJ0 + DEMAND + RNNoiseRealMANVoiceBank+DEMANDDEMAND

Benchmark Results

#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