TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/xLSTM-SENet

xLSTM-SENet

Reported on 10 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio10 results

  • Speech EnhancementonVB-DemandEx
    SSNR· 2025-07-01
    7.933
    SOTA
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonVB-DemandEx
    ESTOI· 2025-07-01
    0.795
    best: 0.801 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonVB-DemandEx
    Number of parameters (M)· 2025-07-01
    2.2
    best: 2.33 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonVB-DemandEx
    PESQ (wb)· 2025-07-01
    2.973
    best: 3.026 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonVB-DemandEx
    SI-SDR· 2025-07-01
    16.414
    best: 16.684 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonDeep Noise Suppression (DNS) Challenge
    ESTOI· 2025-07-01
    95.4
    best: 95.9 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonDeep Noise Suppression (DNS) Challenge
    Number of parameters (M)· 2025-07-01
    2.2
    best: 15 (TF-Locoformer (M))
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonDeep Noise Suppression (DNS) Challenge
    PESQ-WB· 2025-07-01
    3.588
    best: 3.81 (ZipEnhancer (M))
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonDeep Noise Suppression (DNS) Challenge
    SI-SDR-WB· 2025-07-01
    20.854
    best: 23.3 (TF-Locoformer (M))
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966
  • Speech EnhancementonDeep Noise Suppression (DNS) Challenge
    SSNR· 2025-07-01
    14.526
    best: 15.116 (MambAttention)
    MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementarXiv:2507.00966