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/U-Net + TFiLM

U-Net + TFiLM

Reported on 9 benchmarks across 3 tasks · 1 paper

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

Audio9 results

  • Audio GenerationonPiano
    Log-Spectral Distance· 2019-09-14
    2
    best: 3.4 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • Audio GenerationonVoice Bank corpus (VCTK)
    Log-Spectral Distance· uses extra data· 2019-09-14
    2.5
    best: 3.2 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • 10-shot image generationonPiano
    Log-Spectral Distance· 2019-09-14
    2
    best: 3.4 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • 10-shot image generationonVoice Bank corpus (VCTK)
    Log-Spectral Distance· uses extra data· 2019-09-14
    2.5
    best: 3.2 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • Audio Super-ResolutiononPiano
    Log-Spectral Distance· 2019-09-14
    2
    best: 3.4 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • Audio Super-ResolutiononVoice Bank corpus (VCTK)
    Log-Spectral Distance· uses extra data· 2019-09-14
    2.5
    best: 3.2 (U-Net)
    Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise ModulationsarXiv:1909.06628
  • Audio GenerationonVCTK Multi-Speaker
    Log-Spectral Distance
    1.8
    best: 3.1 (U-Net)
  • 10-shot image generationonVCTK Multi-Speaker
    Log-Spectral Distance
    1.8
    best: 3.1 (U-Net)
  • Audio Super-ResolutiononVCTK Multi-Speaker
    Log-Spectral Distance
    1.8
    best: 3.1 (U-Net)