Taejun Kim

MIR Researcher, Software/ML Engineer

About Me

When I was an undergraduate, I took semesters off to be a guitarist but had to program for a living. However, I realized I enjoy programming and quite good at it so I came back to school. Since then I have improved my software and data engineering skills but my passion for music was aroused again so I joined Music and Audio Computing Lab dreaming of making AI DJ. The first research I wanted to do for AI DJ was making a machine listening system, therefore I’ve worked on end‐to‐end audio classification.

I also worked as a resident DJ at a dance club called Vent until before COVID‐19 and still enjoy playing music at events. With the domain knowledge, I work on understanding the creative process of DJing using computational methods and creating AI DJ.

I’ve been wondering how people see beauty in music, and somehow, I currently work on building machines that can understand the beauty and assist music for humans.

Publications

Reverse-Engineering The Transition Regions of Real-World DJ Mixes using Sub-band Analysis with Convex Optimization

Taejun Kim, Yi-Hsuan Yang, and Juhan Nam

Proceedings of the International Conference on New Interfaces for Musical Expression (NIME), 2021

A Computational Analysis of Real-World DJ Mixes using Mix-To-Track Subsequence Alignment

Taejun Kim, Minsuk Choi, Evan Sacks, Yi-Hsuan Yang, and Juhan Nam

Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2020

Comparison and Analysis of SampleCNN Architectures for Audio Classification

Taejun Kim, Jongpil Lee, and Juhan Nam

IEEE Journal of Selected Topics in Signal Processing, 2019

Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms

Taejun Kim, Jongpil Lee, and Juhan Nam

Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

Raw Waveform-based Audio Classification Using Sample-level CNN Architectures

Jongpil Lee, Taejun Kim, Jiyoung Park, and Juhan Nam

Machine Learning for Audio Signal Processing Workshop, Neural Information Processing Systems (NIPS), 2017

Education

Korea Advanced Institute of Science and Technology (KAIST)

Ph.D Student in Graduate School of Culture Technology

2019 - present

@ Music and Audio Computing Lab (Advisor: Juhan Nam)

University of Seoul

M.S. in Electrical and Computer Engineering

2017 - 2019

@ Data Mining Lab (Advisor: Hanjoon Kim)

University of Seoul

B.S. in Electrical and Computer Engineering

2012 - 2017

Research Interests

AI DJ, Music Information Retrieval, Machine Learning, Signal Processing, Musical Applications

Skills

Machine Learning

PyTorch, Scikit‐learn, Weights & Biases, TensorFlow

Data Engineering

Crawling, Elasticsearch, MongoDB, AWS Batch, Apache Spark

Data Analysis

Pandas, Numpy, Matplotlib, SQL, Jupyter Lab, Apache Zeppelin

Signal Processing

Librosa, Madmom, SciPy

Cloud Engineering

(Experienced in AWS) AWS Batch, Step Functions, Lambda, Cognito, S3, Elastic Beanstalk, API Gateway, Cloudfront, etc.

Web Development

Vue.js, Flask, Node.js, AWS Amplify

Programming

Python, JavaScript, Scala, SQL, R, Java

Musical Performance

Vinyl & Digital DJ, Electric Bass Guitar, Acoustic Fingerstyle Guitar