Speech Reconstruction on LibriSpeech clean (test)
4.31UTMOS ScoreStableCodec
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| StableCodecToken Rate=25, Layers=Single-layer2026.01 | 4.31 | 5.7 | 2.6 | 79.3 | 0.93 | 0.91 | — | — | — | — | — | — | — | |
| DTM-Codec@50HzParams=127M, Frame Rate=50, Content=700, Pos=100, Total bps=8002026.06 | 4.22 | 2.91 | — | — | — | — | 78 | 2.66 | — | 93 | — | — | 3.39 | |
| FlexiCodec (τ = 1.0)Params=450M, Frame Rate=12.46, Content=1234, Pos=37, Total bps=12712026.06 | 4.2 | 2.25 | — | — | — | — | 85 | 2.82 | — | 94 | — | — | 3.2 | |
| DTM-Codec@80HzParams=127M, Frame Rate=80, Content=1120, Pos=160, Total bps=12802026.06 | 4.2 | 2.98 | — | — | — | — | 87 | 2.95 | — | 95 | — | — | 3.42 | |
| FlexiCodec (τ = 0.91)Params=450M, Frame Rate=8.26, Content=818, Pos=25, Total bps=8432026.06 | 4.19 | 2.35 | — | — | — | — | 78 | 2.46 | — | 92 | — | — | 3.17 | |
| DTM-Codec@40HzParams=127M, Frame Rate=40, Content=560, Pos=80, Total bps=6402026.06 | 4.19 | 3.27 | — | — | — | — | 74 | 2.49 | — | 92 | — | — | 3.43 | |
| PASTToken Rate=400, Layers=Multi-layer2026.01 | 4.18 | 2.1 | 0.7 | 82.4 | 0.99 | 0.92 | — | — | — | — | — | — | — | |
| BiCodecToken Rate=50, Layers=Single-layer2026.01 | 4.18 | 2.5 | 0.9 | 75 | 0.98 | 0.91 | — | — | — | — | — | — | — | |
| Kanade 12.5HzToken Rate=12.5, Layers=Single-layer2026.01 | 4.17 | 3.3 | 1.3 | 74.6 | 0.97 | 0.85 | — | — | — | — | — | — | — | |
| Kanade 25HzToken Rate=25, Layers=Single-layer2026.01 | 4.16 | 2.4 | 0.8 | 75 | 0.97 | 0.88 | — | — | — | — | — | — | — | |
| FlexiCodec (τ = 0.867)Params=450M, Frame Rate=6.23, Content=617, Pos=19, Total bps=6362026.06 | 4.14 | 2.8 | — | — | — | — | 71 | 2.19 | — | 90 | — | — | 3.14 | |
| X-Codec 2Token Rate=50, Layers=Single-layer2026.01 | 4.13 | 2.5 | 0.9 | 77 | 0.98 | 0.9 | — | — | — | — | — | — | — | |
| VAETraining Data (hrs)=60002026.05 | 4.13 | 4.07 | — | — | 0.97 | — | — | — | — | 98 | — | — | — | |
| Semantic-VAETraining Data (hrs)=60002026.05 | 4.13 | 4.07 | — | — | 0.97 | — | — | — | — | 98 | — | — | — | |
| X-Codec 2.0Params=210M, Frame Rate=50, Content=800, Pos=0, Total bps=8002026.06 | 4.13 | 2.57 | — | — | — | — | 82 | 2.44 | — | 92 | — | — | 3.23 | |
| Semantic-VAEFrame/s=40, Dim=642026.06 | 4.129 | — | — | — | — | — | — | 3.968 | — | 98.1 | — | — | — | |
| DualCodecToken Rate=100, Layers=Multi-layer2026.01 | 4.12 | 2.1 | 0.7 | 75.6 | 0.98 | 0.95 | — | — | — | — | — | — | — | |
| FACodecToken Rate=480, Layers=Multi-layer2026.01 | 4.11 | 2.1 | 0.7 | 81.4 | 0.98 | 0.94 | — | — | — | — | — | — | — | |
| BigCodecFrame rate=80Hz, Codebook size(s)=81922026.06 | 4.11 | 3.6 | — | — | 0.84 | — | — | 2.68 | — | 93.5 | — | 2.93 | — | |
| BigCodecParams=159M, Frame Rate=80, Content=1040, Pos=0, Total bps=10402026.06 | 4.11 | 2.87 | — | — | — | — | 84 | 2.68 | — | 94 | — | — | 3.36 | |
| DTM-Codec@25HzParams=127M, Frame Rate=25, Content=350, Pos=50, Total bps=4002026.06 | 4.11 | 4.73 | — | — | — | — | 58 | 2.07 | — | 90 | — | — | 3.37 | |
| SARAFrame/s=50, Dim=642026.06 | 4.1 | — | — | — | — | — | — | 4.389 | — | 99.3 | — | — | — | |
| XCodec2+SGFrame rate=50Hz, Codebook size(s)=655362026.06 | 4.1 | 3.2 | — | — | 0.8 | — | — | 2.39 | — | 91.5 | — | 3.41 | — | |
| Vanilla VAEFrame/s=50, Dim=642026.06 | 4.095 | — | — | — | — | — | — | 4.076 | — | 98.3 | — | — | — | |
| StableToken#C=1, Frame Rate=25Hz, BPS=3252025.09 | 4.09 | 3.84 | — | — | — | — | — | — | — | — | — | — | — | |
| Ground Truth2026.05 | 4.09 | 3.64 | — | — | 1 | — | — | — | — | 100 | — | — | — | |
| XCodec2Frame rate=50Hz, Codebook size(s)=81922026.06 | 4.09 | 4.1 | — | — | 0.72 | — | — | 2.03 | — | 89.2 | — | 3.84 | — | |
| Ground Truth2026.06 | 4.09 | 2.08 | — | — | — | — | 100 | 4.64 | — | 100 | — | — | 3.23 | |
| GT2026.06 | 4.086 | — | — | — | — | — | — | — | — | — | — | — | — | |
| XCodec2+SGFrame rate=50Hz, Codebook size(s)=81922026.06 | 4.08 | 3.8 | — | — | 0.73 | — | — | 2.13 | — | 89.8 | — | 3.6 | — | |
| Ground Truth2026.01 | 4.07 | 1.9 | 0.6 | 78 | — | — | — | — | — | — | — | — | — | |
| KM 25HzToken Rate=252026.01 | 4.07 | 2.7 | 1 | 72.4 | 0.96 | 0.67 | — | — | — | — | — | — | — | |
| GLM-4-Voice-Token.#C=1, Frame Rate=12.5Hz, BPS=1752025.09 | 4.07 | 4.04 | — | — | — | — | — | — | — | — | — | — | — | |
| XCodec2Frame rate=50Hz, Codebook size(s)=655362026.06 | 4.06 | 3.2 | — | — | 0.79 | — | — | 2.28 | — | 91 | — | 3.57 | — | |
| BigCodecFrame rate=40Hz, Codebook size(s)=81922026.06 | 4.05 | 6.7 | — | — | 0.66 | — | — | 2.11 | — | 89.4 | — | 3.72 | — | |
| KM 12.5HzToken Rate=12.52026.01 | 4.04 | 3 | 1.1 | 72.1 | 0.96 | 0.66 | — | — | — | — | — | — | — | |
| WavCubeTraining Data (hrs)=9602026.05 | 4.04 | 4.2 | — | — | 0.94 | — | — | — | — | 97 | — | — | — | |
| DAC (16k)Params=76M, Frame Rate=50, Content=8000, Pos=0, Total bps=80002026.06 | 4.02 | 2.14 | — | — | — | — | 95 | 3.97 | — | 97 | — | — | 3.09 | |
| WavCube-ProTraining Data (hrs)=60002026.05 | 4 | 4.12 | — | — | 0.95 | — | — | — | — | 97 | — | — | — | |
| WavTokenizer (70Hz)Params=80.9M, Frame Rate=75, Content=900, Pos=0, Total bps=9002026.06 | 4 | 4.32 | — | — | — | — | 68 | 2.38 | — | 91 | — | — | 2.76 | |
| TAAE (700 bps)Params=950M, Frame Rate=25, Content=700, Pos=0, Total bps=7002026.06 | 3.92 | 6.21 | — | — | — | — | 57 | 2.16 | — | 91 | — | — | 3.1 | |
| Cont. 50HzToken Rate=50Hz2026.01 | 3.9 | 2 | 0.6 | 72.1 | 0.99 | 0.94 | — | — | — | — | — | — | — | |
| STToken Rate=400, Layers=Multi-layer2026.01 | 3.9 | 2.1 | 0.7 | 76 | 0.98 | 0.92 | — | — | — | — | — | — | — | |
| WavTokenizerFrame rate=75Hz, Codebook size(s)=40962026.06 | 3.89 | 6.8 | — | — | 0.59 | — | — | 2.05 | — | 88.6 | — | 4 | — | |
| TS3CodecFrame rate=50Hz, Codebook size(s)=655362026.06 | 3.85 | 3.6 | — | — | 0.68 | — | — | 2.22 | — | 90.9 | — | 3.52 | — | |
| TS3CodecFrame rate=50Hz, Codebook size(s)=1310722026.06 | 3.84 | 3.6 | — | — | 0.68 | — | — | 2.23 | — | 91 | — | 3.5 | — | |
| TAAE (400 bps)Params=950M, Frame Rate=25, Content=400, Pos=0, Total bps=4002026.06 | 3.81 | 9.39 | — | — | — | — | 53 | 2 | — | 89 | — | — | 3.03 | |
| WavTokenizer (40Hz)Params=80.9M, Frame Rate=40, Content=480, Pos=0, Total bps=4802026.06 | 3.78 | 8.16 | — | — | — | — | 57 | 1.88 | — | 87 | — | — | 3.11 | |
| WavTokenizerFrame rate=40Hz, Codebook size(s)=40962026.06 | 3.77 | 8 | — | — | 0.57 | — | — | 1.88 | — | 86.8 | — | 4.32 | — | |
| VARSTok (τ = 0.8)Params=80.9M, Frame Rate=34.52, Content=414, Pos=69, Total bps=4832026.06 | 3.74 | 10.51 | — | — | — | — | 50 | 1.69 | — | 86 | — | — | 3.08 | |
| TS3CodecFrame rate=40Hz, Codebook size(s)=1310722026.06 | 3.73 | 4.5 | — | — | 0.63 | — | — | 2.06 | — | 89.7 | — | 3.75 | — | |
| TS3CodecFrame rate=40Hz, Codebook size(s)=655362026.06 | 3.69 | 4.9 | — | — | 0.61 | — | — | 2.01 | — | 89.3 | — | 3.81 | — | |
| VARSTok (τ = 0.7)Params=80.9M, Frame Rate=29.03, Content=348, Pos=58, Total bps=4062026.06 | 3.64 | 15.39 | — | — | — | — | 43 | 1.54 | — | 84 | — | — | 3.03 | |
| Mel-spectrogramTraining Data (hrs)=5852026.05 | 3.63 | 3.86 | — | — | 0.93 | — | — | — | — | 98 | — | — | — | |
| VocosFrame/s=93.75, Dim=1002026.06 | 3.625 | — | — | — | — | — | — | 3.605 | — | 97.7 | — | — | — | |
| VARSTok (τ = 0.6)Params=80.9M, Frame Rate=25.02, Content=300, Pos=50, Total bps=3502026.06 | 3.58 | 20.69 | — | — | — | — | 37 | 1.46 | — | 82 | — | — | 3.01 | |
| WavTokenizerToken Rate=40, Layers=Single-layer2026.01 | 3.57 | 9.4 | 4.7 | 72.1 | 0.92 | 0.91 | — | — | — | — | — | — | — | |
| S3 Tokenizer#C=1, Frame Rate=25Hz, BPS=3002025.09 | 3.4 | 5.78 | — | — | — | — | — | — | — | — | — | — | — | |
| CosyVoice2#C=1, Frame Rate=25Hz, BPS=3252025.09 | 3.36 | 4.25 | — | — | — | — | — | — | — | — | — | — | — | |
| SNAC (12+23+47 Hz)Params=19.8M, Frame Rate=12+23+47, Content=980, Pos=0, Total bps=9802026.06 | 3.05 | 4.39 | — | — | — | — | 58 | 1.91 | — | 88 | — | — | 2.84 | |
| Baseline (Mel/Fbank)Adaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 3.6 | — | 97.8 | 84.9 | — | — | |
| DACFrame rate=50Hz, Codebook size(s)=1024 × 82026.06 | — | — | — | — | 0.87 | — | — | 2.72 | — | 94 | — | — | — | |
| DACFrame rate=50Hz, Codebook size(s)=1024 × 22026.06 | — | — | — | — | 0.32 | — | — | 1.13 | — | 73 | — | — | — | |
| DAS-VAEAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 3.98 | — | 97.9 | 88.8 | — | — | |
| DAS-VAEAdaptive Weighting=true2026.04 | — | — | — | — | — | — | — | 2.73 | — | 94 | 74.3 | — | — | |
| EnCodecAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 2.77 | — | 93.8 | 74.6 | — | — | |
| JMAS-VAEAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 3.97 | — | 97.8 | 88.6 | — | — | |
| JMAS-VAEAdaptive Weighting=true2026.04 | — | — | — | — | — | — | — | 3.84 | — | 97.3 | 87.1 | — | — | |
| Semantic-VAEAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 3.97 | — | 98.1 | 88.8 | — | — | |
| TAS-VAEAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 3.97 | — | 97.7 | 88.6 | — | — | |
| TAS-VAEAdaptive Weighting=true2026.04 | — | — | — | — | — | — | — | 2.92 | — | 94.7 | 76.6 | — | — | |
| Vanilla VAEAdaptive Weighting=false2026.04 | — | — | — | — | — | — | — | 4.12 | — | 98.5 | 90.5 | — | — | |
| VevoReference=from [11]2025.11 | — | 15 | — | — | — | — | 62 | 1.15 | 0.7 | 421 | — | — | — |