Speech Reconstruction on LibriSpeech English (test-clean)
0.97SIMMOSS-Audio-Tokenizer
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.02 | 0.97 | 0.97 | 3.95 | 3.69 | |
| MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.03 | 0.97 | 0.97 | 3.95 | 3.69 | |
| MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.02 | 0.96 | 0.97 | 3.9 | 3.61 | |
| MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.03 | 0.96 | 0.97 | 3.9 | 3.61 | |
| Qwen3-TTS-Tokenizerbps=2200, Frame rate=12.5, NVQ=162026.02 | 0.95 | 0.96 | 3.66 | 3.19 | |
| MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.02 | 0.95 | 0.96 | 3.78 | 3.41 | |
| Qwen3-TTS-Tokenizerbps=2200, Frame rate=12.5, NVQ=162026.03 | 0.95 | 0.96 | 3.66 | 3.19 | |
| MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.03 | 0.95 | 0.96 | 3.78 | 3.41 | |
| Mimibps=4400, Frame rate=12.5, NVQ=322026.02 | 0.94 | 0.96 | 3.8 | 3.43 | |
| Mimibps=4400, Frame rate=12.5, NVQ=322026.03 | 0.94 | 0.96 | 3.8 | 3.43 | |
| MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.02 | 0.92 | 0.95 | 3.64 | 3.2 | |
| MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.03 | 0.92 | 0.95 | 3.64 | 3.2 | |
| MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.02 | 0.91 | 0.95 | 3.73 | 3.25 | |
| MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.03 | 0.91 | 0.95 | 3.73 | 3.25 | |
| Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.02 | 0.9 | 0.85 | 3.59 | 3.11 | |
| Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.03 | 0.9 | 0.85 | 3.59 | 3.11 | |
| MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.02 | 0.89 | 0.95 | 3.57 | 3.05 | |
| Mimibps=2475, Frame rate=12.5, NVQ=182026.02 | 0.89 | 0.94 | 3.49 | 2.97 | |
| DACbps=6000, Frame rate=75, NVQ=82026.02 | 0.89 | 0.95 | 3.75 | 3.41 | |
| MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.03 | 0.89 | 0.95 | 3.57 | 3.05 | |
| Mimibps=2475, Frame rate=12.5, NVQ=182026.03 | 0.89 | 0.94 | 3.49 | 2.97 | |
| DACbps=6000, Frame rate=75, NVQ=82026.03 | 0.89 | 0.95 | 3.75 | 3.41 | |
| MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.02 | 0.88 | 0.94 | 3.38 | 2.87 | |
| MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.03 | 0.88 | 0.94 | 3.38 | 2.87 | |
| Encodecbps=4500, Frame rate=75, NVQ=62026.02 | 0.86 | 0.92 | 2.91 | 2.46 | |
| Encodecbps=4500, Frame rate=75, NVQ=62026.03 | 0.86 | 0.92 | 2.91 | 2.46 | |
| XY-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.02 | 0.85 | 0.92 | 3.1 | 2.5 | |
| SpeechTokenizerbps=4000, Frame rate=50, NVQ=82026.02 | 0.85 | 0.92 | 3.05 | 2.6 | |
| XY-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.03 | 0.85 | 0.92 | 3.1 | 2.5 | |
| SpeechTokenizerbps=4000, Frame rate=50, NVQ=82026.03 | 0.85 | 0.92 | 3.05 | 2.6 | |
| BigCodecbps=1040, Frame rate=80, NVQ=12026.02 | 0.84 | 0.93 | 3.27 | 2.68 | |
| BigCodecbps=1040, Frame rate=80, NVQ=12026.03 | 0.84 | 0.93 | 3.27 | 2.68 | |
| XCodec2.0bps=800, Frame rate=50, NVQ=12026.02 | 0.82 | 0.92 | 3.04 | 2.43 | |
| MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.02 | 0.82 | 0.93 | 3.14 | 2.6 | |
| XCodec2.0bps=800, Frame rate=50, NVQ=12026.03 | 0.82 | 0.92 | 3.04 | 2.43 | |
| MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.03 | 0.82 | 0.93 | 3.14 | 2.6 | |
| MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.02 | 0.8 | 0.91 | 2.94 | 2.39 | |
| MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.03 | 0.8 | 0.91 | 2.94 | 2.39 | |
| Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.02 | 0.77 | 0.83 | 3.03 | 2.48 | |
| Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.03 | 0.77 | 0.83 | 3.03 | 2.48 | |
| Mimibps=1100, Frame rate=12.5, NVQ=82026.02 | 0.74 | 0.91 | 2.8 | 2.25 | |
| DACbps=3000, Frame rate=75, NVQ=42026.02 | 0.74 | 0.9 | 2.76 | 2.31 | |
| Mimibps=1100, Frame rate=12.5, NVQ=82026.03 | 0.74 | 0.91 | 2.8 | 2.25 | |
| DACbps=3000, Frame rate=75, NVQ=42026.03 | 0.74 | 0.9 | 2.76 | 2.31 | |
| SpeechTokenizerbps=2000, Frame rate=50, NVQ=42026.02 | 0.66 | 0.88 | 2.38 | 1.92 | |
| SpeechTokenizerbps=2000, Frame rate=50, NVQ=42026.03 | 0.66 | 0.88 | 2.38 | 1.92 | |
| StableCodecbps=700, Frame rate=25, NVQ=22026.02 | 0.62 | 0.91 | 2.91 | 2.24 | |
| StableCodecbps=700, Frame rate=25, NVQ=22026.03 | 0.62 | 0.91 | 2.91 | 2.24 | |
| Encodecbps=1500, Frame rate=75, NVQ=22026.02 | 0.6 | 0.85 | 1.94 | 1.56 | |
| Encodecbps=1500, Frame rate=75, NVQ=22026.03 | 0.6 | 0.85 | 1.94 | 1.56 | |
| DACbps=1500, Frame rate=75, NVQ=22026.02 | 0.48 | 0.83 | 1.87 | 1.48 | |
| DACbps=1500, Frame rate=75, NVQ=22026.03 | 0.48 | 0.83 | 1.87 | 1.48 | |
| SpeechTokenizerbps=1000, Frame rate=50, NVQ=22026.02 | 0.36 | 0.77 | 1.59 | 1.25 | |
| SpeechTokenizerbps=1000, Frame rate=50, NVQ=22026.03 | 0.36 | 0.77 | 1.59 | 1.25 |