Jin Lee
Research Scientist Intern
Meta

  

Me.

I am a research scientist intern at Meta in Redmond and study machine learning, physical modeling, and numerical simulation, involving audio, music, speech, and acoustics. My research interests include efficient simulation of wave propagation in the field of music and acoustics based on audio signal processing and machine learning.


Education

2019 - 2024 Ph.D. in Intelligence and Information, Seoul National University (SNU)


Thesis: Physical Modeling for String Instrument Sound Synthesis based on Finite-difference Scheme and Automatic Differentiation
Advisor: Kyogu Lee

2013 - 2019 B.Sc. in Mechanical Engineering, Pohang University of Science and Technology (POSTECH)


Thesis: Deep Learning Approach in Multi-scale Prediction of Turbulent Mixing-layer

Previous Positions

Redmond, WA, 2024

Research Scientist Intern, Meta (with Sebastian Prepeliţă)

Seoul, KR, 2021,2023

Research Scientist Intern, Supertone (with Hyeong-Seok Choi)

2019

Research Intern, Music and Audio Research Group, SNU

2018

Research Intern, Robotics Lab, POSTECH

2017

Research Intern, Flow Physics & Engineering Lab, POSTECH

2014

Visiting Student, Korea National University of Arts

Publications

[Google Scholar]
Selected publications are highlighted.


2024

1. Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation [TL;DR] [demo]
Jin Woo Lee, Jaehyun Park, Min Jun Choi, and Kyogu Lee
NeurIPS 2024
2. Inverse Nonlinearity Compensation of Hyperelastic Deformation in Dielectric Elastomer for Acoustic Actuation [TL;DR]
Jin Woo Lee, Gwangseok An, Jeong-Yun Sun, and Kyogu Lee
submitted to IEEE Access 2024
3. String Sound Synthesizer on GPU-accelerated Finite Difference Scheme [TL;DR] [code] [demo] [poster]
Jin Woo Lee, Min Jun Choi, and Kyogu Lee
ICASSP 2024

2023

4. AECSQI: Referenceless Acoustic Echo Cancellation Measures using Speech Quality and Intelligibility Improvement [TL;DR] [slides]
Jin Woo Lee, Hyeong-Seok Choi, and Kyogu Lee
WASPAA (Oral Presentation) 2023
5. Neural Fourier Shift for Binaural Speech Rendering [TL;DR] [code] [demo] [poster]
Jin Woo Lee and Kyogu Lee
ICASSP 2023
6. Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features [TL;DR] [code] [demo] [poster]
Jin Woo Lee, Sungho Lee, and Kyogu Lee
ICASSP 2023

2022 and earlier

7. Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification [TL;DR] [slides]
Jin Woo Lee, Eungbeom Kim, Junghyun Koo, and Kyogu Lee
Interspeech (Oral Presentation) 2022
8. Deep Learning Approach in Multi-scale Prediction of Turbulent Mixing-layer [TL;DR]
Jin Woo Lee, Sangseung Lee, and Donghyun You
arXiv 2019

Invited Talks

1. 2024 Physics-based Differentiable Sound Rendering and Machine Listening, University of Iowa, Dept. of Communication Sciences and Disorders Seminar (host: Inyong Choi)
2. 2024 Differentiable Physical Modeling for Sound Synthesis: From Design to Inverse Problems, Stanford CCRMA, DSP Seminar (host: Julius O. Smith)
3. 2024 Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation, Korea Advanced Institute of Science & Technology (KAIST), Music and Audio Computing Lab (host: Juhan Nam)
4. 2023 Towards Sound Synthesis using Physical Modeling and Differentiable Finite Difference Schemes, SANE Workshop, New York University (NYU)
5. 2023 Differentiable Finite Difference Schemes for Sound Synthesis, AIIS Workshop, Seoul National University
6. 2023 AECSQI: Referenceless Acoustic Echo Cancellation Measures using Speech Quality and Intelligibility Improvement, WASPAA Oral Presentation
7. 2023 NFS: Neural Fourier Shift for Binaural Speech Rendering, Music and Audio Workshop, Seoul National University
8. 2023 Sound Synthesis and Physical Modeling, MARG NSS Seminar, Seoul National University
9. 2022 Neural Fourier Shift for Binaural Speech Rendering, AIIS Workshop, Seoul National University
10. 2022 On the Hyperelastic Deformation of Dielectric Elastomer Actuator and its Acoustic Actuation, Pohang University of Science and Technology (POSTECH)
11. 2022 HRTF Simulation using Boundary Element Method and Neural Network-based Interpolation, Electronics and Telecommunications Research Institute (ETRI)
12. 2022 RSSD: Representation Selective Self-Distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification, Interspeech Oral Presentation
13. 2021 Current Challenges in Head-related Transfer Function Simulation, Electronics and Telecommunincations Research Institute (ETRI)

Academic Services

Reviewing

International Conference on Learning Representations (ICLR)
International Speech Communication Association (ISCA) Interspeech
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Teaching

Machine Listening (TA) SNU M3309.002900
Physical Modeling and Numerical Sound Synthesis (TA) SNU MARG-NSS

Skills

Programming C, C++, Python
Frameworks JAX, NumPy, Pandas, PyTorch, SciPy, TensorFlow
Softwares Comsol, Blender

Last updated on 2024-10-11