Yu, X. et al. 2026. MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 21 (Mar. 2026), 17966–17974. DOI:https://doi.org/10.1609/aaai.v40i21.38856.