Minje Kim, Ph.D.

Bio: Minje Kim is an Associate Professor in the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. Before then, he was an Associate Professor at Indiana University (2016-2023) and Amazon Scholar (2020-2026). He earned his Ph.D. in Computer Science at UIUC (2016) after working as a researcher at ETRI, a national lab in Korea (2006 to 2011). Prior to that, he received his Master’s and Bachelor’s degrees in the Department 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 is a recipient of various awards, including the NSF Career Award (2021), IU Trustees Teaching Award (2021), IEEE SPS Best Paper Award (2020), Google and Starkey’s grants for outstanding student papers in ICASSP 2013 and 2014, respectively, and Richard T. Cheng Endowed Fellowship from UIUC in 2011. He is the Chair of the IEEE SPS Audio and Acoustic Signal Processing Technical Committee (2025-2026). He is serving as Senior Area Editor for IEEE Transactions on Audio, Speech, and Language Processing and IEEE Signal Processing Letters, Advisory Board Member for Journal of Audio, Speech, and Music Processing, and Consulting Associate Editor for IEEE Open Journal of Signal Processing. He served as the General Chair of IEEE WASPAA 2023 and also as a reviewer, program committee member, or area chair for major machine learning and signal processing venues. He is the inventor of more than 60 patents.

My Research Team

Ph.D. Candidates

Tsun-An Hsieh

Intro: Tsun-An joined my group in 2022 at IU, but then he moved with me to UIUC. He has already been knowledgeable in the ML literature, including transfer learning, metric learning, and causal inference, but lately, he developed his interests and expertise in developing generative models with a focus on making them efficient and effective. Application-wise, he has worked on dereveberation, target speaker extraction, and personalized speech enhancement. Before joining my group, he was a research assistant at Academia Sinica and received his Master’s degree at National Taiwan University. He interned at MSR and Meta.

Homepage: https://alexiehta.github.io
Email: tsunanh2-at-illinois-dot-edu
CV: HTML

Jaesung Bae

Intro: Jaesung joined my group in 2024, bringing a rich experience in speech technology gained during his master’s degree at KAIST and as a researcher at NCSOFT and Samsung Research. His research has focused on the intersection of speech synthesis, generative models, and data efficiency in ML. For his PhD study, he has extensively worked on improving the usability of weakly or unlabeled data by introducing generative models to the data augmentation tasks. He is working on challenging speech applications, such as multilingual speech emotion recognition and dysarthric speech processing, where the lack of labeled data is a severe issue. He has been interning at Meta.

Homepage: https://jaesungbae.github.io/
Email: jb82-at-illinois-dot-edu
CV: PDF

Jackie Lin

Intro: Jackie joined the lab in 2024 with her master’s degree from Aalto University in acoustics and audio technology. She has been working on spatial audio and is expanding her interests into generative models for room acoustics simulation and spatial aspects of speech processing applications. Currently, she is working on multichannel audio encoder for general use cases, interpolating/generating room impulses, and acoustic matching problems. She has interned at Adobe Research, MERL, and Shure.

Homepage: https://jackiejqlin.wixsite.com/portfolio
Email: jackiel4-at-illinois-dot-edu
CV: PDF

Cameron Churchwell

Intro: Cameron joined the lab in 2024. He developed his interest in AI-based speech and audio processing tasks, such as speech representation learning, during his undergraduate studies at Northwestern University. For his PhD study, he works on learnable DSP filters with a focus on efficiency and low-delay neural codec designs inspired by differentiable DSP methods, where he often niftily deals with lower-than-Python-level implementation issues. He has been interning at Bose.

Homepage: https://www.cameronchurchwell.com
Email: cc178-at-illinois-dot-edu
CV: PDF

Ph.D. Students

Jayeon Yi

Intro: Jayeon joined the group in 2025 as one of the recipients of the selective Amazon AI PhD Fellowship. He did his master’s degree at the University of Michigan and holds a bachelor’s degree in EE from Seoul National University. He began working on generative neural speech coding, language model-based loss functions, and general-purpose music audio coding.

Homepage: https://stet-stet.github.io
Email: jayeonyi-at-illinois-dot-edu
CV: PDF

Master Students

Jocelyn Xu

Intro: Jocelyn is working on her Master’s thesis on singing voice separation from real-world music recordings. Prior to that, she finished her BS degree in computer science at UIUC with minors in music and statistics.

Homepage: https://www.linkedin.com/in/joosxu/
Email: yuex7-at-illinois-dot-edu
CV:

Yutong Wen

Intro: Prior to joining the lab in 2024, Yutong did his BS degree at the University of Rochester, where he worked on HRTF representation learning. Currently, he is working on the intersection of generative methods and informed source separation, where the side information comes from users’ guidance or example sounds.

Homepage: https://yutongwen.github.io
Email: yutong12-at-illinois-dot-edu
CV: PDF

Charles Cooper

Intro: Charles joined the team with his strong background in CS and mathematics. He is working on signal compression and model compression for the MS thesis.

Homepage: https://ccoop4.github.io
Email: ccoop4-at-illinois-dot-edu
CV: PDF

Visiting Scholars

Wootaek Lim

Intro: Dr. Wootaek Lim is a Visiting Scholar from ETRI, Korea. He is collaborating with the lab on DCASE and neural speech and audio coding. He also brought his expertise in multimodal learning and spatial audio.

Alumni

Ph.D. Alumni

Sanna Wager, Ph.D.

  • Ph.D. in Informatics and minor in Statistics at Indiana University (Spring 2021)
  • Dissertation: “A Data-Driven Pitch Correction Algorithm for Singing Voice” (pdf)
  • The committee: Minje Kim (chair), Christopher Raphael (IU CS), Donald Williamson (IU CS), and Daniel McDonald (U. of British Columbia Statistics)
  • Summary of Ph.D. studies: Dr. Sanna Wager began to work with Minje in fall 2016, and joined the group officially in spring 2017. During her Ph.D. study, she wrote five conference papers on various research topics including tensor decomposition-based multhchannel speech dereverberation, robust speech recognition, semi-supervised methods for collecting a large-scale singing performance dataset, and neural pitch correction algorithms for singing voice. She interned at various companies, such as Google, Smule, Spotify, and Amazon. Her dissertation research on neural pitch correction algorithms for singing received extensive media coverage, including BBC, The Times, Daily Mail, the New Scientist Magazine, etc. She is now at Amazon as an Applied Scientist.

Kai Zhen, Ph.D.

  • Ph.D. (dual degree) in Computer Science and Cognitive Science at Indiana University (Spring 2021)
  • Dissertation: “Neural Waveform Coding: Scalability, Efficiency, and Psychoacoustic Calibration” (pdf)
  • The committee: Minje Kim (chair), Robert Goldstone (IU Cognitive Science), Donald Williamson (IU Computer Science), and Shen Yi (U. of Washington, Speech and Hearing Sciences)
  • Homepage: http://www.kaizhen.us
  • Summary of Ph.D. studies: Dr. Kai Zhen joined the lab in fall 2017 and led multiple neural waveform coding projects, which pioneered a new research area. His papers were published in leading signal processing and speech processing conferences and journals, such as Interspeech, ICASSP, IEEE Signal Processing Letters, and IEEE T-ASLP. The Cognitive Science Program at IU recognized his research by awarding the Outstanding Research Award in 2021. During his Ph.D. study, Dr. Zhen interned at LinkedIn (2018 and 2019) and Amazon (2020). During his internship at Amazon, his work on efficient neural ASR systems was selected as one of the 17 best poster presentations out of 180 internship projects. He is now at Amazon as a Senior Applied Scientist.

Sunwoo Kim, Ph.D.

  • Ph.D. in Intelligent Systems Engineering and minor in Computer Science at Indiana University (Spring 2022)
  • Dissertation: “Model Compression for Efficient Machine Learning Inference” (pdf)
  • The committee: Minje Kim (chair), Peter Todd (IU Cognitive Science), Christopher Raphael (IU Computer Science), and Fan Chen (IU ISE)
  • Summary of Ph.D. studies: Dr. Sunwoo Kim joined the lab in Fall 2017 and has focused on developing efficient machine learning models, such as bitwise neural networks, boosted hashing methods, and knowledge distillation. Out of various papers he published, his ICASSP 2020 paper was recognized as the Best Student Paper runner-up. He interned at Qualcomm (2019) and Amazon (2020 and 2021). He is now at Qualcomm as a Senior Machine Learning Engineer.

R. David Badger, Ph.D.

  • Ph.D. in Intelligent Systems Engineering at Indiana University (Spring 2022)
  • Dissertation: “Open-Source Classification Systems for Frequency-Domain RF Signals: Robust Physical Layer Multi-Sample Rate Processing” (pdf)
  • The committee: Minje Kim (chair), Lei Jiang (IU ISE), Lantao Liu (IU ISE), and Ariful Azad (IU ISE)
  • Summary of Ph.D. studies: Dr. R. David Badger joined the lab in Fall 2018. He has worked on RF signal processing, with a focus on signal compression and classification. He has open-sourced his dataset and deep learning-based RF classification system, which was the first of its kind that aims at multi-class RF signal classification using neural networks. After the Ph.D. he worked at Naval Surface Warfare Center Crane Division, and now he is in the defense sector.

Aswin Sivaraman, Ph.D.

  • Ph.D. in Intelligent Systems Engineering and minor in Computer Science at Indiana University (Spring 2024)
  • Dissertation: “Resource-Efficient Model Adaptation Methods for Personalized Speech Enhancement Systems”
  • The committee: Minje Kim (chair), Christopher Raphael (IU Computer Science), David Crandall (IU Computer Science), and Ariful Azad (IU ISE)
  • Homepage: https://actuallyaswin.github.io
  • Summary of Ph.D. studies: Dr. Aswin Sivaraman joined the lab in Fall 2017 and has focused on developing efficient machine learning models and data augmentation techniques, such as data purification, self-supervised learning from noisy signals, mixture of local experts, etc., for personalized speech enhancement. He wrote three conference papers (Interspeech and WASPAA) and one journal article (IEEE JSTSP) as the first author. He interned at Amazon, Spotify, Microsoft, and Google. He is now at Apple as a Machine Learning Engineer.

Anastasia Kuznetsova, Ph.D.

  • Ph.D. (dual degree) in Computer Science and Linguistics at Indiana University (Spring 2025)
  • Dissertation: “Data Efficiency and Model Complexity Reduction for Speech Processing Systems”
  • The committee: Minje Kim (chair), Francis Tyers (IU Linguistics; co-chair), Damir Cavar (IU Linguistics), David Crandall (IU CS)
  • Homepage: https://ana-kuznetsova.github.io
  • Summary of Ph.D. studies: Dr. Anastasia Kuznetsova’s research during her Ph.D. began in the area of speech technology, with a focus on self-supervised learning and low-resource languages. After joining my group, she expanded her interests to include generative data augmentation for speech enhancement, foundational models for multichannel audio, and neural codecs for ASR, which were published at top speech and audio conferences such as Interspeech, ICASSP, and WASPAA. Anastasia interned at Coqui.ai, Rev.com, Google, and Amazon. She is now at the University of Rochester as a PostDoc.

Darius Pétermann, Ph.D.

  • Ph.D. in Intelligent Systems Engineering and minor in Computer Science at Indiana University (Fall 2025)
  • Dissertation: “Efficient Native Neural Sub-band Coding through Residual Feature Representation within Hyper-Autoencoded Reconstruction Propagation Networks”
  • The committee: Minje Kim (chair), Christopher Raphael (IU Computer Science), Lei Jiang (IU ISE), and Ariful Azad (Texas A&M University, Computer Science)
  • Homepage: http://www.dariuspetermann.com
  • Summary of Ph.D. studies: Dr. Darius Pétermann joined the lab in Spring 2021 with prior expertise ranging from music technology, audio engineering, and machine learning. In my group, he has primarily focused on neural audio coding, with a particular emphasis on high-fidelity and precise reconstruction using multiband and residual coding concepts. Other than that, he also worked on spatial music source separation and distance-based speech separation. His productivity extended to his successful internships at MERL, Google, and Netflix, leading to the Best Student Paper Award at ICASSP 2023. He is now at Netflix as a Research Scientist.

Haici Yang

  • Ph.D. in Intelligent Systems Engineering and minor in Computer Science at Indiana University (Fall 2025)
  • Dissertation: “Latent Variable Learning for Generative Neural Audio Codecs”
  • The committee: Minje Kim (chair), Christopher Raphael (IU Computer Science), Roni Khardon (IU Computer Science), and Ariful Azad (Texas A&M University, Computer Science)
  • Homepage: https://haiciyang.github.io
  • Summary of Ph.D. studies: Dr. Haici Yang joined my group in Fall 2019, with her MS degree in Informatics at Beijing University. She has worked on various audio and music projects, but primarily in the are of neural audio coding. She pioneered various novel directions in the neural coding area by proposing a source-aware coding, predictive coding in the coded feature space, and generative de-quantization using latent diffusion (the “LaDiffCodec”). She was also a successful intern at various companies, such as MERL, Adobe Research, and Amazon, where she developed generative speech enhancement and neural audio upmixing models. She is now with Dolby Labs as a Senior Researcher.
M.S. Alumni

Mrinmoy Maity

  • MS in Intelligent Systems Engineering (Spring 2019)
  • Now at Amazon Music Technology Team as a Senior Machine Learning Engineer

Past Visiting Scholars

Jongmo Sung, Ph.D.

  • Dr. Jongmo Sung from ETRI visited the group from Aug. 2017 to Aug. 2018. We collaborated on neural speech and audio coding. Results were published in IEEE TASLP, SPL, ICASSP 2020, and Interspeech 2019.

Misuk Lee, Ph.D.

  • Dr. Misuk Lee from ETRI visited the group from July 2018 to June 2019. We collaborated on neural speech and audio coding. Results were published in IEEE TASLP, SPL, ICASSP 2020, and Interspeech 2019.

Heeyoul (Henry) Choi, Ph.D.

  • Prof. Heeyoul (Henry) Choi is an Associate Professor at Handong Global University. He visited the group from September 2022 to May 2023. While he was also teaching courses at IU, he also collaborated with my group on language model-assisted loss functions for source separation, resulting in a paper published at Interspeech 2024 [pdf].

Inseon Jang, Ph.D.

  • Dr. Inseon Jang from ETRI visited the group from Feb. 2023 to Feb. 2024. We collaborated on personalized neural speech coding and published at ICASSP 2024 [pdf]

Riccardo Miccini

  • Riccardo Miccini was an Industrial PhD Student at the Technical University of Denmark and GN Audio/Jabra, when he visited UIUC during Fall 2024 and Spring 2025. We collaborated on scalable and efficient speech enhancement models, which led to a WASPAA 2025 paper [pdf].