| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio Reconstruction | Common Voice | CVU0.9888 | 21 | |
| Speech Recognition | Common Voice | WER9 | 17 | |
| Automatic Speech Recognition | Common Voice | WER30.6 | 15 | |
| Automatic Speech Recognition | Common Voice English Accents Exp. 1 | WER (US Accent)15.4 | 15 | |
| Speech quality evaluation | Common Voice 17 | Quality Score (NL)2.55 | 14 | |
| Multilingual Automatic Speech Recognition | Common Voice Exp. 3 (test) | WER (US)15.4 | 13 | |
| Automatic Speech Recognition | Common Voice Arabic (test) | WER38.21 | 12 | |
| Automatic Speech Recognition | Common Voice Mandarin (test) | CER17.82 | 12 | |
| Automatic Speech Recognition | Common Voice Spanish (test) | WER24.58 | 12 | |
| Speech Recognition | Common Voice EN | WER6.76 | 11 | |
| Automatic Speech Recognition | Common Voice en 15 | WER8 | 10 | |
| Text-to-Speech | Common Voice en 15 | WER10.8 | 9 | |
| Automatic Speech Recognition | Common Voice (test) | WER8.5 | 9 | |
| Automatic Speech Recognition | Common Voice Unseen Languages | WER43.2 | 8 | |
| Continual Learning for Automatic Speech Recognition | Common Voice Exp. 1 (test) | WER (US)15 | 7 | |
| Voice Cloning | Common Voice English | SIM Score0.81 | 7 | |
| Automatic Speech Recognition | Common Voice Singaporean | WER4.9 | 7 | |
| Automatic Speech Recognition | Common Voice Indian | WER0.057 | 7 | |
| Automatic Speech Recognition | Common Voice Australian | WER (%)4.3 | 7 | |
| Automatic Speech Recognition | Common Voice African | WER4.6 | 7 | |
| Automatic Speech Recognition | Common Voice 15 | English WER7.61 | 6 | |
| Automatic Speech Recognition | Common Voice 16.1 (test) | WER (de)7.8 | 5 | |
| Speech Recognition | Common Voice German (test) | WER12.94 | 5 | |
| Speech Recognition | Common Voice Polish (test) | WER3.61 | 5 | |
| Speech Transmission Latency Analysis | Common Voice untrained (test) | TCoder (ms)0.0008 | 5 |