Li, Yinghao Aaron, Xilin Jiang, Fei Tao, Cheng Niu, Kaifeng Xu, Juntong Song, and Nima Mesgarani. “DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 38 (March 14, 2026): 31814-31822. Accessed May 4, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40450.