Junhyeok Lee

text-to-speech synthesis (3) neural vocoder (2) audio upsampling (2) reward modeling (1) talking face generation (1) face animation (1) policy optimization (1) adversarial training (1) signal-to-noise ratio (1) bayesian optimization (1) adversarial attack (1) black-box attack (1) diffusion model (1) generative adversarial network (1) classifier-free guidance (1) multi-agent cooperation (1) preference-based reinforcement learning (1) latent diffusion model (1) diffusion probabilistic model (1) speech synthesis (1)