Sungho Lee

Sungho Lee sh-lee at snu.ac.kr scholar github linkedin cv

I am a postdoctoral researcher at the Machine Learning & Vision Lab, KAIST. I primarily work on audio inverse problems in domains such as room acoustics and audio effects. I received my Ph.D. from the Music and Audio Research Group, Seoul National University, and previously interned at Meta Reality Labs, Sony AI, and Supertone.

Recent Updates

2026.09Starting as a postdoctoral researcher at KAIST.
2026.08Received Ph.D. from Seoul National University.
2026.08Visited the Institute of Sound Recording, University of Surrey, for an invited talk.
2026.07Got 1 first-author paper accepted at ISMIR.
2026.04Started a research internship at Meta Reality Labs.
2026.04Got 1 first-author paper accepted at IEEE TASLPRO.
2026.01Started a research internship at Sony AI.

Selected Publications

Solving Inverse Problems of Audio Systems with Differentiable Processing and Generative Modeling

Sungho Lee

Ph.D. dissertation, Seoul National University, 2026pdf
Exploring the Design Space of Representation Learning for Audio Transformations

Sungho Lee, Marco A. Martínez-Ramírez, Junghyun Koo, Wei-Hsiang Liao, Kyogu Lee, Yuki Mitsufuji

ISMIR, 2026
Differentiable Acoustic Radiance Transfer

Sungho Lee, Matteo Scerbo, Seungu Han, Min Jun Choi, Kyogu Lee, Enzo De Sena

IEEE TASLPRO, 2026arXiv
Reverse Engineering of Music Mixing Graphs with Differentiable Processors and Iterative Pruning

Sungho Lee, Marco A. Martínez-Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee, Yuki Mitsufuji

JAES, 2025demo JAES arXiv code
GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch

Sungho Lee, Marco A. Martínez-Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee, Yuki Mitsufuji

DAFx demo, 2024arXiv code docs
Yet Another Generative Model for Room Impulse Response Estimation

Sungho Lee, Hyeong-Seok Choi, Kyogu Lee

WASPAA, 2023demo arXiv
Blind Estimation of Audio Processing Graph

Sungho Lee, Jaehyun Park, Seungryeol Paik, Kyogu Lee

ICASSP, 2023demo arXiv
Differentiable Artificial Reverberation

Sungho Lee, Hyeong-Seok Choi, Kyogu Lee

IEEE/ACM TASLP, 2022demo arXiv