Liang Y, Li A, Yang K, Yu G, Liu F, Dai L, et al. SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 17];40(38):31943-51. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40464