38 citations · 51 across the 3 of their papers we have counts for
3 papers
cs.SD2017
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…
stat.ML2016★ 38 cited
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…
cs.SD2015★ 13 cited
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…