Fang L, Xie T, Liu L. Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards. AAAI [Internet]. 2026Mar.14 [cited 2026May4];40(36):30673-81. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40323