| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Speech Synthesis | LJ Speech (test) | MOS4.54 | 36 | |
| Automatic Speech Recognition | LJ-Speech | WER3.33 | 35 | |
| Speech Recognition | LJ-Speech (test) | WER3.01 | 35 | |
| Audio Generation | LJ Speech (test) | LL Score5.161 | 20 | |
| Text-to-Speech | LJ Speech (val) | Time to 5% WER2.5 | 6 |