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/Spleeter (MWF)

Spleeter (MWF)

Reported on 10 benchmarks across 2 tasks

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

Music5 results

  • Music Source SeparationonMUSDB18
    SDR (avg)· uses extra data
    5.91
    best: 9.2 (Sparse HT Demucs (fine tuned))
  • Music Source SeparationonMUSDB18
    SDR (bass)· uses extra data
    5.51
    best: 10.47 (Sparse HT Demucs (fine tuned))
  • Music Source SeparationonMUSDB18
    SDR (drums)· uses extra data
    6.71
    best: 10.83 (Sparse HT Demucs (fine tuned))
  • Music Source SeparationonMUSDB18
    SDR (other)· uses extra data
    4.02
    best: 7.08 (Band-Split RNN (semi-sup.))
  • Music Source SeparationonMUSDB18
    SDR (vocals)· uses extra data
    6.86
    best: 10.47 (Band-Split RNN (semi-sup.))

Methodology5 results

  • 2D ClassificationonMUSDB18
    SDR (avg)· uses extra data
    5.91
    best: 9.2 (Sparse HT Demucs (fine tuned))
  • 2D ClassificationonMUSDB18
    SDR (bass)· uses extra data
    5.51
    best: 10.47 (Sparse HT Demucs (fine tuned))
  • 2D ClassificationonMUSDB18
    SDR (drums)· uses extra data
    6.71
    best: 10.83 (Sparse HT Demucs (fine tuned))
  • 2D ClassificationonMUSDB18
    SDR (other)· uses extra data
    4.02
    best: 7.08 (Band-Split RNN (semi-sup.))
  • 2D ClassificationonMUSDB18
    SDR (vocals)· uses extra data
    6.86
    best: 10.47 (Band-Split RNN (semi-sup.))