Audio Super Resolution On Vctk Multi Speaker 1
평가 지표
Log-Spectral Distance
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Log-Spectral Distance | Paper Title | Repository |
|---|---|---|---|
| U-Net | 3.1 | Audio Super Resolution using Neural Networks | |
| NVSR | 0.78 | Neural Vocoder is All You Need for Speech Super-resolution | |
| TUNet + MSM pre-training | 1.28 | TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining | |
| U-Net + TFiLM | 1.8 | Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations. | |
| CMGAN | 0.76 | CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement | |
| TUNet | 1.36 | TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining | |
| U-Net + AFiLM | 1.7 | Self-Attention for Audio Super-Resolution |
0 of 7 row(s) selected.