Hyeongju Kim

text-to-speech synthesis (2) normalizing flow (2) flow-based model (2) diffusion model (2) probabilistic model (1) 3d generation (1) denoising diffusion (1) controllable generation (1) classifier-free guidance (1) latent diffusion model (1) multi-channel speech (1) speech naturalness (1) speaker fidelity (1) phoneme-level modeling (1) speech editing (1) score-based generative modeling (1) manifold learning (1) score-based modeling (1) point cloud generation (1) automatic speech recognition (1)