Ben Hayes

prof_pic.jpg

I am a PhD student in Artificial Intelligence and Music at Queen Mary University of London’s Centre for Digital Music. My research blends digital signal processing and deep learning for audio synthesis and processing. I am particularly interested in differentiable digital signal processing (DDSP) and how this methodology can help us incorporate signal processing knowledge into deep learning systems. I am jointly supervised by Dr Charalampos Saitis and Dr György Fazekas, and am very grateful to be funded by the UKRI Centre for Doctoral Training in Artificial Intelligence and Music.

Previously, I was a research scientist intern at Spotify (Music Intelligence), Sony CSL (Music Team), and Bytedance (Speech, Audio & Music Intelligence), and lead the music team at Jukedeck. I have also worked extensively as a music producer, and was a lecturer in Electronic & Produced Music at the Guildhall School of Music & Drama in London.

You can contact me at b.j.hayes (at) qmul.ac.uk

selected publications

  1. Frontiers
    A Review of Differentiable Digital Signal Processing for Music & Speech Synthesis
    Ben Hayes, Jordie Shier, György Fazekas, and 2 more authors
    Frontiers in Signal Processing, 2023
  2. ICLR
    The Responsibility Problem in Neural Networks with Unordered Targets
    Ben Hayes, Charalampos Saitis, and George Fazekas
    In The First Tiny Papers Track at ICLR 2023, Tiny Papers @ ICLR 2023, Kigali, Rwanda, May 5, 2023, 2023
  3. ICASSP
    Sinusoidal Frequency Estimation by Gradient Descent
    Ben Hayes, Charalampos Saitis, and George Fazekas
    In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
  4. ICASSP
    Rigid-Body Sound Synthesis with Differentiable Modal Resonators
    Rodrigo Diaz, Ben Hayes, Charalampos Saitis, and 2 more authors
    In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023