Fang, L., T. Xie, and L. Liu. “Boosting ASR Robustness via Test-Time Reinforcement Learning With Audio-Text Semantic Rewards”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 36, Mar. 2026, pp. 30673-81, doi:10.1609/aaai.v40i36.40323.