Jonah Casebeer

Hi there, I’m a third year Ph.D. candidate in Computer Science at the University of Illinois Urbana-Champaign (UIUC). I also completed my undergraduate studies at UIUC where I majored in Statistics & Computer Science. I’m interested in building tools which blend between analytic signal processing methods and data-driven machine learning approaches to make faster, better, and easier to design models. In this line of work, I’ve worked on approaches for acoustic echo cancellation, equalization, dereverberation, and beamforming.

I am advised by Paris Smaragdis and have had the chance to work with some great collaborators including Nick Bryan, Umut Isik, and Ivan Dokmanic. Feel free to check out what we’ve done on my publications page or my Google Scholar page.

You might also be interested in the work done by my lab mates: Efthymios Tzinis, Zhepei Wang, and Krishna Subramani

news

Apr, 2022 Our pre-print: “Meta-AF: Meta-Learning for Adaptive Filters” is up! Check it out here.
Apr, 2022 For the 2022 summer I’ll be working at Facebook Reality Labs with Jacob Donley!
Sep, 2021 Our papers “Auto-DSP: Learning to Optimize Acoustic Echo Cancellers”, “Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data” and “Sound Event Detection with Adaptive Frequency Selection” have all been accepted at WASPAA 2021.
Sep, 2021 For the 2021 fall semester I’ll be working with Nicholas J. Bryan at Adobe Research!
Apr, 2021 For the 2021 summer I’ll be working at Facebook Reality Labs with Jacob Donley!

selected publications

  1. Meta-AF: Meta-Learning for Adaptive Filters
    Casebeer, Jonah, Bryan, Nicholas J., and Smaragdis, Paris
    arXiv preprint arXiv:2204.11942 2022
  2. NICE-Beam: Neural Integrated Covariance Estimators for Time-Varying Beamformers
    Casebeer, Jonah, Donley, Jacob, Wong, Daniel, Xu, Buye, and Kumar, Anurag
    arXiv preprint arXiv:2112.04613 2022
  3. Auto-DSP: Learning to Optimize Acoustic Echo Cancellers
    Casebeer, Jonah, Bryan, Nicholas J, and Smaragdis, Paris
    In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021
  4. Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
    Casebeer, Jonah, Vale, Vinjai, Isik, Umut, Valin, Jean-Marc, Giri, Ritwik, and Krishnaswamy, Arvindh
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021
  5. Deep Tensor Factorization for Spatially-Aware Scene Decomposition
    Casebeer, Jonah, Colomb, Michael, and Smaragdis, Paris
    In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2019