Kyogu Lee

Professor@Seoul National University·韩国·OpenReview

研究方向

deep learning; generative models; multimodal learning · audio signal processing; speech signal processing; music signal processing · speech synthesis; singing voice synthesis

3.5

UNISE: Unified Noise-Invariant Learning for Speech Enhancement toward Improved Content Preservation

ICLR 2026Rejected

通讯

7.0

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction

NeurIPS 2025Poster

二作

5.5

Multidimensional Trajectory Optimization for Flow and Diffusion

ICLR 2025Rejected

通讯

4.8

Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion

ICML 2025Poster

通讯

3.3

Solving Blind Non-linear Forward and Inverse Problem for Audio Applications

合作者 (15)