Papers › Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement

Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement

21 Dec 2024arXiv:2412.16626archive 2025-07-28

Junyu Wang, Zizhen Lin, Tianrui Wang, Meng Ge, Longbiao Wang, Jianwu Dang

In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment. Mamba, as a novel state-space model (SSM), has gained widespread application in natural language processing and computer vision due to its strong capabilities in modeling long sequences and relatively low computational complexity. In this work, we introduce Mamba-SEUNet, an innovative architecture that integrates Mamba with U-Net for SE tasks. By leveraging bidirectional Mamba to model forward and backward dependencies of speech signals at different resolutions, and incorporating skip connections to capture multi-scale information, our approach achieves state-of-the-art (SOTA) performance. Experimental results on the VCTK+DEMAND dataset indicate that Mamba-SEUNet attains a PESQ score of 3.59, while maintaining low computational complexity. When combined with the Perceptual Contrast Stretching technique, Mamba-SEUNet further improves the PESQ score to 3.73.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

MambaSpeech Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) CBAK 3.67 #3 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) COVL 4.40 #3 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) CSIG 4.82 #3 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) PESQ (wb) 3.73 #3 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) Para. (M) 6.28 #3 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND Mamba-SEUNet L (+PCS) STOI 96 #3 of 42 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Concatenated Skip ConnectionConvolutionMambaMax PoolingReLUU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections