| LibriTTS clean (test) | BigVGAN | PESQ4.186 | | 50 | 3d ago |
| LibriSpeech (test-clean) | | STOI1 | | 49 | 3d ago |
| LibriTTS (test-other) | Sylber | UTMOS3.91 | | 44 | 3d ago |
| AISHELL-2 Chinese | MOSS-Audio-Tokenizer | SIM0.93 | | 27 | 3d ago |
| LibriSpeech English (test-clean) | MOSS-Audio-Tokenizer | SIM0.97 | | 27 | 3d ago |
| Chinese speech | SAC | UTMOS2.99 | | 19 | 3d ago |
| English speech | WavTokenizer | UTMOS3.92 | | 19 | 3d ago |
| SeedTTS en (test) | | WER0.0214 | | 18 | 3d ago |
| Salmon Sentiment Consistency emotional 2025b (OOD) | | WER2.9 | | 18 | 3d ago |
| LibriSpeech clean (test) | | WER1.9 | | 15 | 3d ago |
| SEED-EN | H-Codec-2.0 (Large) | PESQ2.77 | | 12 | 3d ago |
| SEED-ZH | H-Codec-2.0 (Large) | PESQ2.88 | | 12 | 3d ago |
| Open Track 2 (test) | Baseline | ScoreQ-ref1.15 | | 12 | 3d ago |
| Open Track 1 (test) | Baseline | ScoreQ-ref1.36 | | 12 | 3d ago |
| English Read by Japanese accented speech 2007 (OOD) | | WER14.9 | | 9 | 3d ago |
| Japanese Versatile Speech unseen language speech 2019 (OOD) | | WER4.6 | | 9 | 3d ago |
| Gigaspeech noisy speech 2021 (OOD) | | WER9.7 | | 9 | 3d ago |
| Librispeech (test) | MSR-Codec-612 | STOI0.9 | | 8 | 3d ago |
| LibriTTS (test) | VCNAC | PESQ4.16 | | 7 | 3d ago |
| VCTK subset | ReasoningCodec | PESQ (WB)2.36 | | 7 | 3d ago |
| GRID (speaker-dependent) | Proposed Method | STOI0.738 | | 7 | 3d ago |
| LRAC Challenge Track 1 (Multi-talkers) 2025 (test) | Baseline | DMOS1.26 | | 6 | 4d ago |
| LRAC Challenge Track 1 (Noisy) 2025 (test) | 1st place | DMOS4.44 | | 6 | 4d ago |
| LRAC Challenge Track 1 (Clean) 2025 (test) | 1st place | MUSHRA Score81.75 | | 6 | 3d ago |
| LibriSpeech and LJSpeech | | MUSHRA Score98.08 | | 6 | 3d ago |
