Sungwon Kim

Researcher, NVIDIA

Joined

September 2021

Names

Sungwon Kim (Preferred)

Emails

****@snu.ac.kr (Confirmed)

****@gmail.com (Confirmed)

****@nvidia.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

NVIDIA (nvidia.com)

2024 – Present

PhD student

Seoul National University (snu.ac.kr)

2019 – 2024

MS student

Seoul National University (snu.ac.kr)

2017 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Sungroh Yoon

2016 – 2024

Expertise

Deep generative models

Text-to-speech

Speech synthesis

Present

Publications

PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
Rajarshi Roy, Jonathan Raiman, Sang-gil Lee, Teodor-Dumitru Ene, Robert Kirby, Sungwon Kim, Jaehyeon Kim, Bryan Catanzaro
- ICASSP 2026
- Readers: Everyone
ETTA: Elucidating the Design Space of Text-to-Audio Models
Sang-gil Lee, Zhifeng Kong, Arushi Goel, Sungwon Kim, Rafael Valle, Bryan Catanzaro
- ICML 2025 poster
- Readers: Everyone
A$^2$-Flow: Alignment-Aware Pre-training for Speech Synthesis with Flow Matching
Sungwon Kim, Sang-gil Lee, Alexander H. Liu, Joao Felipe Santos, Mikyas T. Desta, Sudheer Kovela, Rafael Valle, Bryan Catanzaro
- Submitted to ICLR 2025
- Readers: Everyone
Fugatto 1: Foundational Generative Audio Transformer Opus 1
Rafael Valle, Rohan Badlani, Zhifeng Kong, Sang-gil Lee, Arushi Goel, Sungwon Kim, Joao Felipe Santos, Shuqi Dai, Siddharth Gururani, Aya Aljafari, Alexander H. Liu, Kevin J. Shih, Ryan Prenger, Wei Ping, Chao-Han Huck Yang, Bryan Catanzaro
- ICLR 2025 Poster
- Readers: Everyone
Elucidating the Design Space of Text-to-Audio Models
Sang-gil Lee, Zhifeng Kong, Arushi Goel, Sungwon Kim, Rafael Valle, Bryan Catanzaro
- Submitted to ICLR 2025
- Readers: Everyone
P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
Sungwon Kim, Kevin J. Shih, Rohan Badlani, Joao Felipe Santos, Evelina Bakhturina, Mikyas T. Desta, Rafael Valle, Sungroh Yoon, Bryan Catanzaro
- NeurIPS 2023 poster
- Readers: Everyone
AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate
Jongyoon Song, Sungwon Kim, Sungroh Yoon
- 10 Apr 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
FICGAN: Facial Identity Controllable GAN for De-identification
Yonghyun Jeong, Jooyoung Choi, Sungwon Kim, Youngmin Ro, Tae-Hyun Oh, Doyeon Kim, Heonseok Ha, Sungroh Yoon
- 18 Nov 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, Sungroh Yoon
- 18 Nov 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Perception Prioritized Training of Diffusion Models
Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon
- 2022 (modified: 24 Apr 2023)
- CVPR 2022
- Readers: Everyone

View all 20 publications

Co-Authors

View all 37 co-authors