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/SepFormer

SepFormer

Reported on 9 benchmarks across 2 tasks · 2 papers · 8 SOTA

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

Audio6 results

  • Speech EnhancementonWHAMR!
    SDR· 2022-02-06
    12.29
    SOTA
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884
  • Speech EnhancementonWHAMR!
    SI-SNR· 2022-02-06
    10.58
    SOTA
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884
  • Speech EnhancementonWHAM!
    PESQ· 2022-02-06
    3.07
    SOTA
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884
  • Speech EnhancementonWHAM!
    SDR· 2022-02-06
    15.04
    SOTA
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884
  • Speech EnhancementonWHAM!
    SI-SNR· 2022-02-06
    14.35
    SOTA
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884
  • Speech EnhancementonWHAMR!
    PESQ· 2022-02-06
    2.84
    best: 3.5 (WD-TCN)
    Exploring Self-Attention Mechanisms for Speech SeparationarXiv:2202.02884

Speech3 results

  • Speech SeparationonWSJ0-2mix
    SDRi· 2020-10-25
    22.4
    best: 25.2 (TF-Locoformer (L) + DM)
    SOTA
    Attention is All You Need in Speech SeparationarXiv:2010.13154
  • Speech SeparationonWSJ0-2mix
    SI-SDRi· 2020-10-25
    22.3
    best: 25.1 (TF-Locoformer (L) + DM)
    SOTA
    Attention is All You Need in Speech SeparationarXiv:2010.13154
  • Speech SeparationonWSJ0-3mix
    SI-SDRi· 2020-10-25
    19.5
    best: 23.7 (SepTDA)
    SOTA
    Attention is All You Need in Speech SeparationarXiv:2010.13154