Open access
2026
Toward Extremely Low-Bit and Multi-Precision Conformer and Speech Foundation Model Quantization
Evaluations show that QACT provides a high-accuracy solution when retraining is affordable, whereas CSVQ offers efficient compression under strict computational budgets.
Zhao-Qing Li, Haoning Xu, Zengrui Jin et al.
· IEEE Transactions on Audio,... · 0 citations