The Grainger College of Engineering

Minje Kim

Minje Kim
Minje Kim he/him/his
  • Associate Professor

For More Information

Education

  • Ph.D. in Computer Science, University of Illinois at Urbana-Champaign (2016)
  • M.S. in Computer Science and Engineering, POSTECH (2006)
  • B.E. in Information and Computer Engineering, Ajou University (2004)

Biography

Minje Kim is an Associate Professor in the School of Computing and Data Science at the University of Illinois at Urbana-Champaign and an Amazon Scholar. Before then, he was an Associate Professor at Indiana University (2016-2023). He earned his Ph.D. in Computer Science at UIUC (2016). He worked as a researcher at ETRI, a national lab in Korea, from 2006 to 2011. He received his Master's and Bachelor's degrees in the Dept. of Computer Science and Engineering at POSTECH (Summa Cum Laude) and in the Division of Information and Computer Engineering at Ajou University (with honors) in 2006 and 2004, respectively. During his career as a researcher, he has focused on developing machine learning models for audio signal processing applications. He has been on more than 60 patents as an inventor.

Academic Positions

  • Associate Professor, Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, 2024 - present
  • Associate Professor, Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing and Engineering, Indiana University, 2022 - 2023

Other Professional Employment

  • Researcher, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea, 2006-2011

Major Consulting Activities

  • Amazon Scholar, Amazon.com Inc., Sunnyvale, CA (Jul. 2020 - present)

Teaching Statement

Learning from various modalities is important. Problem-solving is the best way to learn new things. Loves to interact with students.

Resident Instruction

  • CS448 Audio Computing Laboratory (Spring 2026)
  • CS545 Machine Learning for Signal Processing (Fall 2025)
  • CS598GMA Generative Models for Audio (Spring 2025)
  • CS545 Machine Learning for Signal Processing (Fall 2024)

Research Statement

Minje Kim has focused on improving the efficiency and scalability of machine learning models for audio applications. He developed model compression methods that use fewer computing resources for on-device processing, proposed the "personalization" concept that scales down the task to focus on specific users’ voices, and scalable model architectures that adapt to the dynamically changing resource constraints. These algorithms have been successfully used to solve various audio problems, such as signal enhancement, source separation, speech and audio compression, spatial audio, etc.

Research Interests

  • AI for Audio
  • Model Compression
  • Personalized AI
  • Source Separation
  • Speech Enhancement
  • Neural Speech and Audio Coding

Selected Articles in Journals

  • Minje Kim and Jan Skoglund, “Neural Speech and Audio Coding: Modern AI Technology Meets Traditional Codecs,” IEEE Signal Processing Magazine, vol. 41, no. 6, pp. 85-93, Nov. 2024.
  • Sunwoo Kim, Mrudula Athi, Guangji Shi, Minje Kim, and Trausti Kristjansson, "Zero-Shot Test-Time Adaptation Via Knowledge Distillation for Personalized Speech Denoising and Dereverberation," Journal of the Acoustical Society of America, Vol. 155, No. 2, pp. 1353-1367, Feb. 2024.
  • Aswin Sivaraman and Minje Kim, "Efficient Personalized Speech Enhancement through Self-Supervised Learning," IEEE Journal of Selected Topics in Signal Processing, vol. 16, no. 6, pp. 1342-1356, Oct. 2022.
  • Sunwoo Kim and Minje Kim, "Boosted Locality Sensitive Hashing: Discriminative, Efficient, and Scalable Binary Codes for Source Separation," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 2659-2672, Aug. 2022.
  • Kai Zhen, Mi Suk Lee, Jongmo Sung, Seungkwon Beack, and Minje Kim, "Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding," IEEE Signal Processing Letters, vol. 27, pp. 2159-2163, 2020.
  • Kai Zhen, Jongmo Sung, Mi Suk Lee, Seungkwon Beack, and Minje Kim, "Scalable and Efficient Neural Speech Coding: A Hybrid Design," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol 30, pp. 12-25, 2022.
  • Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, and Paris Smaragdis, "Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 23, no. 12, pp. 2136-2147, Dec. 2015.

Journal Editorships

  • Senior Area Editor, IEEE Signal Processing Letters
  • Senior Area Editor, IEEE Transactions in Audio, Speech and Language Processing

Professional Societies

  • Chair, Reviews Subcommittee, IEEE SPS Audio and Acoustic Signal Processing Technical Committee, 2022
  • Member, International Speech Communication Association (ISCA)
  • Member, IEEE Signal Processing Society
  • Senior Member IEEE

Honors

  • Richard T. Cheng Endowed Fellowship (2011)

Teaching Honors

  • Indiana University Trustees Teaching Award, 2021 (2021)
  • UIUC, Dept. of Computer Science, Outstanding Teaching Assistant, 2015 (2015)

Research Honors

  • NSF CAREER Award, 2021 (2021)
  • IEEE Signal Processing Society Best Paper Award, 2020 (2020)
  • Starkey Signal Processing Research Student Grant, 2014 (2014)
  • Google ICASSP Student Travel Grant, 2013 (2013)

Recent Courses Taught

  • CS 448 - Audio Computing Laboratory
  • CS 545 - Machine Learning for Signals
  • CS 598 GMA - Generative Models for Audio

Related News