Ji-Hoon Kim

speech synthesis (3) waveform generation (2) text-to-speech synthesis (2) question answering (2) self-supervised learning (2) generative adversarial network (2) conditional flow matching (2) motion estimation (1) video generation (1) adversarial learning (1) voice conversion (1) talking face generation (1) multimodal learning (1) question retrieval (1) information bottleneck (1) cross-modal learning (1) facial animation (1) attention mechanism (1) neural architecture search (1) passage retrieval (1)