List your company

Acoustic and paralinguistic modeling on SALMon

97.2Acoustic Consistency (Sentence)Human
52.79264.32175.8587.379Mar 5, 2026

Evaluation results

MethodLinks
HumanParams=–, Textually Pretrained=–, Codebooks=–2026.0397.291.598.693.3—
LLaMA-Mimi 1.3BParams=1.3B, Textually Pretrained=✓, Codebooks=4 × 20482026.03798583.548.569
WT-SMA-24Params=∼357M, Textually Pretrained=✓, Codebooks=1 × 40962026.0378.56981.550.562.6
LLaMA-Mimi 8BParams=8.0B, Textually Pretrained=✓, Codebooks=4 × 20482026.0376.586.585.546.569.5
WavSLM-2kParams=305M, Textually Pretrained=✗, Codebooks=1 × 20482026.0375.58689.545.568.3
WavSLM-4kParams=307M, Textually Pretrained=✗, Codebooks=1 × 40962026.037588.590.551.569.5
WavSLM-65kParams=370M, Textually Pretrained=✗, Codebooks=1 × 655362026.037587.5844566.5
SpiRit LM Expr.Params=7.0B, Textually Pretrained=✓, Codebooks=[501, 64, 100]2026.0373.581855269.4
Mimi-S-24Params=∼357M, Textually Pretrained=✓, Codebooks=8 × 20482026.0371.57877.55264
DWavL-S-16Params=∼357M, Textually Pretrained=✓, Codebooks=6 × 10002026.037086.5924969
LAST 1.3BParams=1.3B, Textually Pretrained=✓, Codebooks=1 × 5002026.036564.568.553.5—
SQ-SMA-16Params=∼357M, Textually Pretrained=✓, Codebooks=4 × 196832026.036484.58350.562.9
HuBERT 25HzParams=∼357M, Textually Pretrained=✓, Codebooks=1 × 5002026.0362.56969.55365.3
TWIST 1.3BParams=1.3B, Textually Pretrained=✓, Codebooks=1 × 5002026.0361.56969.55364.8
TWIST 7BParams=7.0B, Textually Pretrained=✓, Codebooks=1 × 5002026.0361.5717051.566.3
DAC-SMA-16Params=∼357M, Textually Pretrained=✓, Codebooks=8 × 10242026.036077815060.2
ST-S-16Params=∼357M, Textually Pretrained=✓, Codebooks=8 × 10242026.03586566.549.557.2
Enc-SMA-24Params=∼357M, Textually Pretrained=✓, Codebooks=8 × 10242026.0356.56570.55056.1
SpiRit LMParams=7.0B, Textually Pretrained=✓, Codebooks=1 × 5012026.0354.569.5674864.2