John Hershey

2 accepted papers

2026

SURF: Separation via Unsupervised Remixing Flow

Henry Li, Robin Scheibler, Efthymios Tzinis, Matt Shannon, Arnaud Doucet, john hershey

ICML 2026poster

The goal of single-channel source separation is to reconstruct $K$ sources given their mixture. In supervised settings where vast amounts of clean source data are available, this challenging, ill-posed problem has been addressed successfully by generative diffusion and flow-based prior models. Howev…

Cited by 0 Source ↗Scholar ↗

2016

Full-Capacity Unitary Recurrent Neural Networks

Scott Wisdom, Thomas Powers, John Hershey, Jonathan Le Roux, Les Atlas

NeurIPS 2016poster

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recurrence matrices, have recently been proposed as a means to avoid these issues. H…

Cited by 384 Source ↗PDF ↗code ↗Scholar ↗