10-shot image generation on Voice Bank corpus (VCTK)

Metric: Log-Spectral Distance (higher is better)

LeaderboardDataset
Loading chart...
#ModelLog-Spectral DistanceExtra DataPaperDateCode
1U-Net3.2YesAudio Super Resolution using Neural Networks2017-08-02Code
2U-Net + TFiLM2.5YesTemporal FiLM: Capturing Long-Range Sequence Dep...2019-09-14Code
3U-Net + AFiLM2.3YesSelf-Attention for Audio Super-Resolution2021-08-26Code