Zhenhui Ye

speech synthesis (4) diffusion model (3) prosody modeling (2) multimodal learning (2) audio generation (2) contrastive learning (2) text-to-audio generation (2) multitask learning (1) talking face generation (1) zero-shot learning (1) multi-modal learning (1) semantic alignment (1) cross-modal learning (1) speech enhancement (1) facial animation (1) preference learning (1) generative model (1) reinforcement learning from human feedback (1) cross-modal alignment (1) prosody prediction (1)