Minje Kim, PhD

Bio: I’m an assistant professor at Indiana University Bloomington. I’m with the Department of Intelligent Systems Engineering at the School of Informatics, Computing, and Engineering. I earned my PhD in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Before joining UIUC, I worked as a researcher in ETRI, a national lab in Korea, from 2006 to 2011. I received my Bachelor’s and Master’s degrees in the Division of Information and Computer Engineering at Ajou University (with honor) and in the Department of Computer Science and Engineering at POSTECH (Summa Cum Laude) in 2004 and 2006, respectively. My research focuses on developing machine learning algorithms applied to audio processing, stressing their computational efficiency in the resource-constrained environments or in the applications involving large unorganized datasets. To this end, I developed some machine learning algorithms, such as manifold preserving topic models, deflation methods for nonnegative matrix factorization, hashing-based speed-up techniques for topic models, component sharing (or co-factorization) for collaborative audio enhancement from a massive set of crowdsourced recordings, and bitwise neural networks where all computations are carried out in an efficient bitwise fashion, etc. I received Richard T. Cheng Endowed Fellowship from UIUC in 2011. Google and Starkey grants also honored my ICASSP papers as the outstanding student papers in 2013 and 2014, respectively. I was selected as an outstanding teaching assistant for the course “Machine Learning for Signal Processing” in the fall 2015, too.

CV (pdf)




PhD Candidates

Lijiang Guo

Bio: I am a PhD student in the Department of Intelligent Systems Engineering at Indiana University. I am interested in machine learning for signal processing, solving problems in speech enhancement and source separation. I’ve studied Statistics and is a PhD candidate in Statistics at Indiana University. Besides research, I enjoy reading sci-fi books, fine-art photography and all kinds of sports. I am an amateur distance runner, and finished the rolling hills of Hoosier Half Marathon in 1h45m.

Email: lijguo-at-indiana-dot-edu


Sanna Wager

Bio: I’m in my fourth year of the Music track of the PhD in Informatics and Computing at Indiana University. My adviser is Minje Kim. My undergraduate degree was in Bassoon Performance at Indiana University’s Jacobs School of Music, studying under Kathleen McLean. My undergraduate minor was math. I am interested in how technology influences the way people relate to music, and how we can use technology to develop our understanding of music. Music has been at the front end of technical innovation for thousands of years. Pythagoras described its deep connection to math, architecture, astronomy, and psychology; Beethoven worked with piano makers to develop instruments that could handle his compositions; conductor Herbert von Karajan was among the first to acquire the newest analog recording devices. I strive to promote interaction between the fields of acoustic music and computing so that the recent innovation in the digital world can be applied in the best possible way to music. I hope to 1) develop knowledge of music representation in technology, so that results are aesthetically convincing, 2) give musicians more general and easy access to training in music technology, and 3) encourage the development of music-related technology that helps the youngest generation connect to high-quality music as listeners and performers.

Email: scwager-at-indiana-dot-edu


Mrinmoy Maity

Bio: Mrinmoy is a PhD student in Computer Science at Indiana University Bloomington with a focus on Deep Learning. More specifically, he is interested in optimizing deep neural networks using less computations and limited storage spaces to enable on device operations on embedded devices in real-time. He mostly focuses on applications in audio domain although his research interests are generic enough to be applied to areas like automated driving and natural language processing. He also holds a broader interests in Artificial Intelligence in areas like Generative models and Reinforcement learning.

Email: mmaity-at-umail-dot-iu-dot-edu


Kai Zhen

Bio: My research in general is on audio, speech and music signal processing in the current machine learning paradigm. I’m currently working on a psychoacoustically enhanced deep neural network with parameter quantization towards a compact and energy efficient speech denoising autoencoder.

Email: zhenk-at-umail-dot-iu-dot-edu




PhD Students

Sun Woo Kim

Bio: I am a second year PhD student studying in CS/ISE. Before IU, I lived in Singapore and then studied Physics at UIUC. Currently, my research interests are in end-to-end systems, latent feature representations, and attention mechanisms. On my free time, I like to watch TV (too much), read books (epics), play board games, and go out to eat. I love meeting people and doing things, have nice conversations so please don’t hesitate to ask 🙂

Email: kimsunw-at-indiana-dot-edu


Aswin Sivaraman

Bio: I am a first-year PhD student at Indiana University (IU) hailing from the Chicago suburbs. I received my BS in Electrical Engineering at the University of Illinois at Urbana-Champaign (UIUC). My current research interests lie in machine learning approaches to speech and music applications, such as audio compression or autotune.

Email: asivara-at-iu-edu




Visiting Scholars

Jongmo Sung, PhD

Bio: I am currently an visiting research scholar at Indiana University Bloomington. I received my BS and MS degrees in electronic engineering from Pusan National University (PNU), Korea, in 1995 and 1997, respectively. I received my PhD in the Intelligent Robot Systems from Chungnam National University (CNU), Korea, in 2014. I worked for LG Electronics (LGE) Inc. from 1997 to 1999. Since 1999, I have been working as a principal  researcher in the Realistic AV Research Group at ETRI, Daejeon in Korea. In ETRI, I was mainly engaged in standardization works for a speech and audio codec with wider range of signal bandwidths and broader functionalities through ITU-T, 3GPP and MPEG. My major contributions were related to develop ITU-T Recommendation G.729.1, G.711.1, G.711.1 Annex D, G.722 Annex B, G.729.1 Annex E and ISO/IEC 23008 Part 3: 3D Audio (a.k.a., MPEG-H 3D Audio). My current research interests include a speech and audio signal processing using machine learning techniques, especially ML-based audio compression/decompression.

Email: sungjong-at-iu-dot-edu