HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Audio Super Resolution On Vctk Multi Speaker 1

Metrics

Log-Spectral Distance

Results

Performance results of various models on this benchmark

Paper TitleRepository
U-Net3.1Audio Super Resolution using Neural Networks
U-Net + TFiLM1.8Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.-
U-Net + AFiLM1.7Self-Attention for Audio Super-Resolution
TUNet1.36TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining
TUNet + MSM pre-training1.28TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining
NVSR0.78Neural Vocoder is All You Need for Speech Super-resolution
CMGAN0.76CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
0 of 7 row(s) selected.
Audio Super Resolution On Vctk Multi Speaker 1 | SOTA | HyperAI