111 citations · 164 across the 5 of their papers we have counts for
5 papers
Differentiable Greedy Networks
Thomas Powers, Rasool Fakoor, Siamak Shakeri +4
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is t…
Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding
Scott Wisdom, Thomas Powers, James Pitton +1
In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterativ…
Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery
Scott Wisdom, Thomas Powers, James Pitton +1
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and lea…
Full-Capacity Unitary Recurrent Neural Networks
Scott Wisdom, Thomas Powers, John R. Hershey +2
Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural…
Enhancement and Recognition of Reverberant and Noisy Speech by Extending Its Coherence
Scott Wisdom, Thomas Powers, Les Atlas +1
Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time sp…