Speech Reconstruction on LibriTTS clean (test)
4.644PESQGT
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GT2026.03 | 4.644 | 1 | — | 4.056 | — | — | — | — | — | — | — | — | |
| BigVGANUnified=true, SR=44.1, Token rate category=Vocoder2026.01 | 4.186 | 0.993 | — | — | — | — | — | — | — | — | — | — | |
| DACBandwidth=9.0kbps, Nq=9, token/s=9002025.12 | 3.9082 | 0.9699 | — | 3.9097 | 97.81 | — | — | — | — | — | — | — | |
| DACNq=9, FPS=9002026.03 | 3.908 | 0.97 | — | 3.91 | — | — | — | — | — | — | — | — | |
| DACUnified=true, TPS=900, kbps=9, Nq=9, SR=44.1, Token rate category=> 1002026.01 | 3.9 | 0.972 | — | — | — | — | — | — | — | — | — | — | |
| Q2D2Bandwidth=6.9kbps, Nq=1, token/s=3332025.12 | 3.7006 | 0.9637 | — | 4.0321 | 97.99 | — | — | — | — | — | — | — | |
| DACParams [M]=74.71, Token Rate=75, Codebook Size=1024, Q=8, Bitrate [kbps]=62025.12 | 3.5215 | 0.9546 | 0.971 | 3.6905 | — | — | — | — | — | — | — | — | |
| DACUnified=true, DR=40, TPF=8, TPS=6002025.02 | 3.5197 | 0.9709 | 0.9546 | 3.6905 | — | — | — | — | — | — | — | — | |
| Q2D2Bandwidth=3.3kbps, Nq=1, token/s=1662025.12 | 3.3635 | 0.9557 | — | 4.0613 | 96.76 | — | — | — | — | — | — | — | |
| Ours Wav-VAENq=1, FPS=11.722026.03 | 3.237 | 0.967 | — | 4.013 | — | — | — | — | — | — | — | — | |
| Ours Wav-VAENq=1, FPS=7.812026.03 | 3.089 | 0.963 | — | 4.116 | — | — | — | — | — | — | — | — | |
| VibeVoiceNq=1, FPS=7.502026.03 | 3.068 | 0.828 | — | 4.181 | — | — | — | — | — | — | — | — | |
| UniCodecUnified=true, DR=320, TPF=1, TPS=752025.02 | 3.0266 | 0.9493 | 0.9486 | 3.9873 | — | — | — | — | — | — | — | — | |
| HiFi-CodecBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 3.0116 | 0.9446 | — | 3.9035 | 95.76 | — | — | — | — | — | — | — | |
| HiFi-CodecBandwidth=4.0kbps, Nq=4, token/s=4002025.12 | 2.9611 | 0.9405 | — | 3.7529 | 96.17 | — | — | — | — | — | — | — | |
| TIREParams=63.33 M2026.07 | 2.956 | 0.944 | — | — | — | — | 4.382 | — | — | 0.699 | — | 0.728 | |
| Dual-TIRE (baseline)Params=63.91 M, segment selection strategy=random (unconstrained)2026.07 | 2.931 | 0.946 | — | — | — | — | 4.387 | — | — | 0.699 | — | 0.727 | |
| Dual-TIRE (cross-file)Params=63.91 M, segment selection strategy=cross-file (same speaker and book)2026.07 | 2.923 | 0.946 | — | — | — | — | 4.41 | — | — | 0.721 | — | 0.741 | |
| UniCodecUnified=true, TPS=75, kbps=1.3, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 2.87 | 0.94 | — | — | — | — | — | — | — | — | — | — | |
| EncodecUnified=true, TPS=600, kbps=6, Nq=8, SR=24, Token rate category=> 1002026.01 | 2.819 | 0.943 | — | — | — | — | — | — | — | — | — | — | |
| VocosNq=8, FPS=6002026.03 | 2.807 | 0.943 | — | 3.695 | — | — | — | — | — | — | — | — | |
| VocosBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 2.8069 | 0.9426 | — | 3.6954 | 94.37 | — | — | — | — | — | — | — | |
| No-TIRE (baseline)Params=63.12 M2026.07 | 2.797 | 0.938 | — | — | — | — | 4.362 | — | — | 0.703 | — | 0.772 | |
| DACBandwidth=4.0kbps, Nq=4, token/s=4002025.12 | 2.7378 | 0.928 | — | 3.4329 | 95.72 | — | — | — | — | — | — | — | |
| UniSRCodec-LUnified=true, TPS=176, kbps=2.29, Nq=1, SR=44.1, Token rate category=> 1002026.01 | 2.727 | 0.941 | — | — | — | — | — | — | — | — | — | — | |
| EncodecUnified=true, DR=40, TPF=8, TPS=6002025.02 | 2.7202 | 0.9391 | 0.9527 | 3.0399 | — | — | — | — | — | — | — | — | |
| EncodecParams [M]=14.85, Token Rate=75, Codebook Size=1024, Q=8, Bitrate [kbps]=62025.12 | 2.7202 | 0.9391 | 0.9527 | 3.0399 | — | — | — | — | — | — | — | — | |
| EncodecBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 2.7202 | 0.9391 | — | 3.0399 | 95.27 | — | — | — | — | — | — | — | |
| EncodecNq=8, FPS=6002026.03 | 2.72 | 0.939 | — | 3.04 | — | — | — | — | — | — | — | — | |
| BigCodecUnified=false, TPS=80, kbps=1.04, Nq=1, SR=16, Token rate category=≤ 1002026.01 | 2.7 | 0.943 | — | — | — | — | — | — | — | — | — | — | |
| BigCodecNq=1, FPS=802026.03 | 2.697 | 0.939 | — | 4.097 | — | — | — | — | — | — | — | — | |
| SACodecParams [M]=75.17, Token Rate=75, Codebook Size=1000 / 1024, Q=2, Bitrate [kbps]=1.52025.12 | 2.6937 | 0.9317 | 0.9381 | 4.0373 | — | — | — | — | — | — | — | — | |
| BigCodecUnified=false, DR=200, TPF=1, TPS=802025.02 | 2.6872 | 0.9293 | 0.948 | 4.0367 | — | — | — | — | — | — | — | — | |
| SpeechTokenizerUnified=false, DR=40, TPF=8, TPS=6002025.02 | 2.6121 | 0.9165 | 0.9495 | 3.8794 | — | — | — | — | — | — | — | — | |
| SpeechTokenizerParams [M]=103.68, Token Rate=50, Codebook Size=1024, Q=8, Bitrate [kbps]=42025.12 | 2.6121 | 0.9165 | 0.9495 | 3.8794 | — | — | — | — | — | — | — | — | |
| SpeechTokenizerBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 2.6121 | 0.9165 | — | 3.8794 | 94.95 | — | — | — | — | — | — | — | |
| WT-SpeechUnified=false, TPS=75, kbps=0.9, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 2.566 | 0.922 | — | — | — | — | — | — | — | — | — | — | |
| SNACUnified=true, TPS=240, kbps=2.88, Nq=4, SR=44.1, Token rate category=> 1002026.01 | 2.561 | 0.925 | — | — | — | — | — | — | — | — | — | — | |
| Q2D2Bandwidth=1kbps, Nq=1, token/s=752025.12 | 2.5091 | 0.9217 | — | 4.0526 | 94.4 | — | — | — | — | — | — | — | |
| WavTokenizerParams [M]=80.55, Token Rate=75, Codebook Size=4096, Q=1, Bitrate [kbps]=0.92025.12 | 2.4687 | 0.9194 | 0.9394 | 3.9687 | — | — | — | — | — | — | — | — | |
| VocosBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 2.4026 | 0.9231 | — | 3.539 | 93.58 | — | — | — | — | — | — | — | |
| Wavtokenizer (speech)Unified=false, DR=320, TPF=1, TPS=752025.02 | 2.373 | 0.9139 | 0.9382 | 4.0486 | — | — | — | — | — | — | — | — | |
| WavTokenizerBandwidth=0.9kbps, Nq=1, token/s=752025.12 | 2.373 | 0.9139 | — | 4.0486 | 93.82 | — | — | — | — | — | — | — | |
| WavTokenizerNq=1, FPS=752026.03 | 2.373 | 0.914 | — | 4.049 | — | — | — | — | — | — | — | — | |
| MimiUnified=true, DR=240, TPF=8, TPS=1002025.02 | 2.2695 | 0.9118 | 0.912 | 3.5731 | — | — | — | — | — | — | — | — | |
| FACodecParams [M]=374.49, Token Rate=80, Codebook Size=1024, Q=6, Bitrate [kbps]=4.82025.12 | 2.2532 | 0.9127 | 0.9402 | 3.4454 | — | — | — | — | — | — | — | — | |
| EncodecUnified=true, TPS=300, kbps=3, Nq=4, SR=24, Token rate category=> 1002026.01 | 2.116 | 0.904 | — | — | — | — | — | — | — | — | — | — | |
| EncodecBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 2.0517 | 0.9007 | — | 2.307 | 91.98 | — | — | — | — | — | — | — | |
| SpeechTokenizerBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 1.9311 | 0.8778 | — | 3.5632 | 92.73 | — | — | — | — | — | — | — | |
| WT-UnifiedUnified=true, TPS=40, kbps=0.48, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 1.912 | 0.875 | — | — | — | — | — | — | — | — | — | — | |
| TAAEUnified=false, DR=320, TPF=2, TPS=502025.02 | 1.8955 | 0.8816 | 0.926 | 4.1389 | — | — | — | — | — | — | — | — | |
| EG-GRVQVQ scheme (Structure)=EG-GRVQ (2x2), Bitrate=0.6875 kbps2026.03 | 1.881 | 0.89 | — | — | — | -7.309 | 2.496 | — | — | — | — | — | |
| Mimi (official)VQ scheme (Structure)=RVQ (1x4), Bitrate=0.6875 kbps2026.03 | 1.872 | 0.876 | — | — | — | 3.451 | 2.01 | — | — | — | — | — | |
| Mimi (GRVQ)VQ scheme (Structure)=GRVQ (2x2), Bitrate=0.6875 kbps2026.03 | 1.852 | 0.889 | — | — | — | -7.294 | 2.464 | — | — | — | — | — | |
| Wavtokenizer (unified)Unified=true, DR=320, TPF=1, TPS=752025.02 | 1.8379 | 0.8718 | 0.9175 | 3.6115 | — | — | — | — | — | — | — | — | |
| UniSRCodec-BUnified=true, TPS=40, kbps=0.52, Nq=1, SR=44.1, Token rate category=≤ 1002026.01 | 1.836 | 0.875 | — | — | — | — | — | — | — | — | — | — | |
| MelCapUnified=true, TPS=260, kbps=3.4, Nq=1, SR=44.1, Token rate category=> 1002026.01 | 1.802 | 0.888 | — | — | — | — | — | — | — | — | — | — | |
| TAAEUnified=false, TPS=50, kbps=0.7, Nq=1, SR=16, Token rate category=≤ 1002026.01 | 1.787 | 0.89 | — | — | — | — | — | — | — | — | — | — | |
| Mimi (retrain)VQ scheme (Structure)=RVQ (1x4), Bitrate=0.6875 kbps2026.03 | 1.779 | 0.886 | — | — | — | -6.969 | 2.546 | — | — | — | — | — | |
| WT-MAUnified=false, TPS=75, kbps=0.9, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 1.747 | 0.857 | — | — | — | — | — | — | — | — | — | — | |
| WavTokenizerBandwidth=0.5kbps, Nq=1, token/s=402025.12 | 1.7027 | 0.8615 | — | 3.6016 | 91.73 | — | — | — | — | — | — | — | |
| EncodecParams [M]=14.85, Token Rate=75, Codebook Size=1024, Q=2, Bitrate [kbps]=1.52025.12 | 1.5398 | 0.8462 | 0.8496 | 1.5551 | — | — | — | — | — | — | — | — | |
| DACParams [M]=74.71, Token Rate=75, Codebook Size=1024, Q=2, Bitrate [kbps]=1.52025.12 | 1.53 | 0.8453 | 0.8957 | 1.9152 | — | — | — | — | — | — | — | — | |
| DACUnified=true, TPS=100, kbps=1, Nq=1, SR=44.1, Token rate category=≤ 1002026.01 | 1.308 | 0.763 | — | — | — | — | — | — | — | — | — | — | |
| SpeechTokenizerParams [M]=103.68, Token Rate=50, Codebook Size=1024, Q=3, Bitrate [kbps]=1.52025.12 | 1.2668 | 0.7853 | 0.8353 | 2.4121 | — | — | — | — | — | — | — | — | |
| DACBandwidth=1.0kbps, Nq=1, token/s=1002025.12 | 1.2464 | 0.7706 | — | 1.494 | 79.41 | — | — | — | — | — | — | — | |
| DACUnified=false, DR=320, TPF=1, TPS=752025.02 | 1.1763 | 0.7739 | 0.756 | 1.3531 | — | — | — | — | — | — | — | — | |
| BiCodecToken Rate (t/s)=502026.06 | — | — | — | 4.25 | — | 26.49 | — | 2.6 | 1.3 | 0.78 | 0.55 | — | |
| CleanCodec@12.5Token Rate (t/s)=12.52026.06 | — | — | — | 4.32 | — | 21.96 | — | 2.7 | 1.4 | 0.86 | 0.44 | — | |
| CleanCodec@31.25Token Rate (t/s)=31.252026.06 | — | — | — | 4.27 | — | 22.02 | — | 1.7 | 0.9 | 0.88 | 0.33 | — | |
| CleanCodec@62.5Token Rate (t/s)=62.52026.06 | — | — | — | 4.23 | — | 22.94 | — | 1.3 | 0.6 | 0.9 | 0.29 | — | |
| FocalCodecToken Rate (t/s)=12.52026.06 | — | — | — | 4.21 | — | 25.19 | — | 8.3 | 4.5 | 0.45 | 0.78 | — | |
| Ground Truth2025.02 | — | — | — | 4.0562 | — | — | — | — | — | — | — | — | |
| GT2025.12 | — | — | — | 4.0562 | — | — | — | — | — | — | — | — | |
| GTToken Rate (t/s)=–2026.06 | — | — | — | 4.2 | — | 26.49 | — | 0 | 0 | 1 | 0 | — | |
| KanadeToken Rate (t/s)=12.52026.06 | — | — | — | 4.22 | — | 23.6 | — | 4 | 2.1 | 0.65 | 0.57 | — | |
| MimiToken Rate (t/s)=1002026.06 | — | — | — | 3.86 | — | 17.48 | — | 3.5 | 1.9 | 0.72 | 0.56 | — | |
| Qwen3Token Rate (t/s)=2002026.06 | — | — | — | 4.27 | — | 27.99 | — | 1.3 | 0.7 | 0.9 | 0.29 | — | |
| Qwen3Token Rate (t/s)=1002026.06 | — | — | — | 3.92 | — | 19.45 | — | 2.6 | 1.4 | 0.72 | 0.38 | — | |
| Qwen3Token Rate (t/s)=502026.06 | — | — | — | 2.65 | — | 9.01 | — | 7.9 | 4.5 | 0.31 | 0.63 | — | |
| WavTokenizerToken Rate (t/s)=402026.06 | — | — | — | 3.81 | — | 19.98 | — | 9 | 5 | 0.62 | 0.46 | — | |
| XCodec2Token Rate (t/s)=502026.06 | — | — | — | 4.2 | — | 23.51 | — | 2.6 | 1.5 | 0.77 | 0.39 | — |