Hello!

Hello, I am Soo-Whan Chung from South Korea.

I joined the Speech team at Naver Corporation as a Research Scientist in November 2020, and I am currently continuing my work at Naver Cloud Corporation.

Within the team, my focus is on general acoustic modeling, which includes speech recognition, preprocessing, and generation. Specifically, I develop various models for speech enhancement, separation, and restoration. I also contribute to the front-end acoustic model for speech recognition. Additionally, I work on modeling efforts aimed at generating natural-sounding audio and speech signals.

I received my Ph.D. degree in the Department of Electrical & Electronic Engineering from Yonsei University. During my doctoral studies, I interned at Naver Clova, which further enriched my research experience.

My research expertise spans a broad spectrum of speech signal processing and multi-modal learning. I specialize in speech enhancement, separation, and restoration, and I have a strong interest in exploring research topics related to audio-visual modalities. Furthermore, I have gained valuable experience in various speech-oriented applications, including speaker recognition, speech synthesis, and speech analysis.

I welcome any collaboration on research projects that align with my interests and expertise in these areas. I am also open to assisting with a diverse range of research topics. Perhaps we can collaborate on writing an academic paper or exploring new research fields.

If you have any questions or would like to discuss potential collaborations, please feel free to contact me via email.

  Download my CV here.

Recent News

[2023,Sep.1] Release LibriPhrase Benchmark
[2023,Jun.1] Accepted 2 new papers at INTERSPEECH 2023
[2023,Mar.1] Accepted 4 new papers at ICASSP 2023
[2022,Sep.22] Nominated as the finalist of the Best Paper Award at INTERSPEECH 2022

Recent Posts