Juntae Kim
Senior Research Engineer at LG AI Research
South Korea
Summary
👤
Senior🎓
Top SchoolJuntae Kim is a Senior Research Engineer with nine years of experience specializing in end-to-end Korean speech recognition, noise-robust and far-field ASR, and speech enhancement techniques. He holds MS and PhD studies in Electrical Engineering from KAIST and has driven research and product work across Kakao, SK Telecom, and LG AI Research. Juntae combines deep learning research with practical toolkit development—his open-source VAD toolkit showcases hands-on contributions to DNN, bDNN, and LSTM-based voice activity detection and dataset collection. Known for tackling challenging audio conditions, he also explores singing voice synthesis and source separation, bridging academic rigor with real-world deployment. Based in South Korea, he brings both published research instincts and engineering discipline to building robust speech and audio systems.
9 years of coding experience
6 years of employment as a software developer
Bachelor's degree Biomedical Engineering, Bachelor's degree Biomedical Engineering at Kyung Hee UniversityDoctor of Philosophy - PhD Electrical Engineering, Doctor of Philosophy - PhD Electrical Engineering at Korea Advanced Institute of Science and Technology
English
Github Skills (7)
machine-learning10
lstm10
tensorflow10
python10
modeling9
trainings9
data-analysis7
Programming languages (3)
Github contributions (5)
jtkim-kaist/VAD
Apr 2017 - Jun 2021
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
Role in this project:
ML Engineer
ML EngineerContributions:118 commits, 112 pushes, 2 branches in 4 years 2 months
Contributions summary:Juntae appears to be focused on improving a Voice Activity Detection (VAD) toolkit, which involves a variety of machine learning techniques. They have made updates to several Python scripts that likely train and test VAD models, including bDNN, DNN, and LSTM-based architectures. Their contributions involve modifications to model training configurations and evaluation procedures, including setting up summary operations for performance tracking. The user also made changes to the overall project structure, including modifying the main.m file.
lstmvoice-activity-detectionvaddnnbdnn
jtkim-kaist/Speech-enhancement
Jun 2018 - Jun 2019
Deep neural network based speech enhancement toolkit
Contributions:30 commits, 42 pushes, 1 branch in 1 year
neural-networkspeech-enhancementspeech-processing
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.