2026
Knowing When to Quit: Probabilistic Early Exits for Speech Separation Networks
Kenny Falkær Olsen, Mads Østergaard, Karl Ulbæk, Søren Føns Nielsen, Rasmus Malik Høegh Lindrup, Bjørn Sand Jensen +1
ICLR 2026poster
In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however, designed with a fixed compute and parameter budget, and consequen…