Scholar
Cem Subakan
Google Scholar ID: zXzV-0UAAAAJ
Assistant Prof. at Laval University, Computer Science Dept. / Mila, Associate Academic Member
Citations & Impact
Citations
2,551
H-index
18
i10-index
24
Publications
20
Co-authors
15
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications include 'Listenable Maps for Audio Classifiers' (accepted to ICML 2024 as an oral presentation), 'REAL-M: Towards Speech Separation on Real Mixtures' (accepted to ICASSP 2022), 'Attention is All You Need in Speech Separation' (accepted to ICASSP 2021); Co-organized XAI-SA 2024 workshop; Multiple papers accepted in various international conferences.
Research Experience
- Did a postdoc at Mila, working with Laurent Charlin; Currently an Assistant Professor in the Computer Science and Software Engineering Department at Université Laval, and an Affiliate Assistant Professor in the Computer Science and Software Engineering Department at Concordia University.
Education
- Obtained B.Sc. and M.Sc. degrees from Bogazici University EE department in 2011 and 2013 respectively, under the supervision of A. Taylan Cemgil and Bulent Sankur; Obtained PhD from the Computer Science Department of the University of Illinois at Urbana-Champaign, with Paris Smaragdis as his advisor.
Background
- Research Interests: Time series modeling, Interpretable Machine Learning, Audio Source separation / Speech Enhancement, Deep Generative Models, Machine Learning, Statistical Learning, Bayesian inference, Non-convex optimization, Method of Moments based learning algorithms for Latent Variable Models. Brief Introduction: He is one of the core contributors to the Speechbrain project, co-organizing the ICASSP 2024 XAI-SA workshop, and will be the general chair of IEEE Workshop of Machine Learning for Signal Processing 2025.
Miscellany
- Personal interests and hobbies not mentioned.
