Audio Super Resolution On Vctk Multi Speaker 1
Metrics
Log-Spectral Distance
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Log-Spectral Distance |
|---|---|
| audio-super-resolution-using-neural-networks | 3.1 |
| neural-vocoder-is-all-you-need-for-speech | 0.78 |
| tunet-a-block-online-bandwidth-extension | 1.28 |
| temporal-film-capturing-long-range-sequence-1 | 1.8 |
| cmgan-conformer-based-metric-gan-for-monaural | 0.76 |
| tunet-a-block-online-bandwidth-extension | 1.36 |
| self-attention-for-audio-super-resolution | 1.7 |