Woojin Chung

Ph.D Student

About

About Me

Deep Learning Programmer / Speech Specialist
Ph.D student in department of Electrical and Electronics at Yonsei University
Research Intrest:
Speech/Audio Signal Processing
Multi-Modal Signal Processing

Download CV

Education

2022 - Present

Doctor of Philosophy

Yonsei University

Department of Electrical & Electronic Engineering, DSP&AI Lab.
Research topics: Speech Synthesis, Multi-Modal Signal Processing
Supervisor: Hong-Goo Kang

2016 - 2022

Bachelor of Engineering

Kyung Hee University

Department of Electronic Engineering

Awards

October 2023

1st place @ BHI 2023 Data Challenge Competition: Sensor Informatic

Pittsburgh, USA

IEEE Healthcare Summit (IHS)

Publications

2024

Patient-Aware Acoustic-to-Articulatory Inversion through Speech SSL Layer Analysis

Woo-Jin Chung, Hong-Goo Kang
2024

Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator

Woo-Jin Chung, Hong-Goo Kang

INTERSPEECH

2024

Optimization of DNN-based speaker verification model through efficient quantization technique

Yeona Hong, Woo-Jin Chung, Hong-Goo Kang

Society of Electronic Engineers of Korea Conference

2024

Contextual Learning for Missing Speech Automatic Speech Recognition

Yeona Hong, Miseul Kim, Woo-Jin Chung, Hong-Goo Kang

International Conference on Electronics, Information, and Communication (ICEIC)

2024

SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition

Juhwan Yoon, Seyun Um, Woo-Jin Chung, Hong-Goo Kang

International Conference on Electronics, Information, and Communication (ICEIC)

2023

MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion

Woo-Jin Chung, Doyeon Kim, Soo-Whan Chung, Hong-Goo Kang

INTERSPEECH

Projects

Mar. 2023 - Present

Brain to X, fully implantable closed circuit for speech communication

Korea Evaluation Institute of Industrial Technology (KEIT)

Main Tasks: Speech Synthesis / Speech Generation / Multi-Modal Signal Processing
- Construct a deep learning-based speech synthesis model using ECoG signals
- Implement a speech synthesis model using articulatory signals
- Design a neural network-based brain auditory speech recognition technology

Mar. 2022 - Dec. 2022

Development of Speech Restoration in various distorted environments

NAVER Corporation

Main Tasks: Speech Enhancement / Speech Restoration / Speech Generation
- Design an speech restoration system through speech generation task
- Enhance frequency bands of speech distorted by reverberation and noise
- Extract speech features from distorted speech for auxiliary information

Contact

Contact Me

Address

C505, 3rd Engineering Building, Yonsei University, 50, Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea 03722

Contact Number

+82 10 6551 0251

Email Address

woojinchung@dsp.yonsei.ac.kr