313 citations · 376 across the 17 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
eess.AS2019
Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
Sunwoo Kim, Minje Kim
We propose an iteration-free source separation algorithm based on Winner-Take-All (WTA) hash codes, which is a faster, yet accurate alternative to a complex machine learning model…
eess.AS2019★ 17 cited
Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
Sunwoo Kim, Mrinmoy Maity, Minje Kim
This paper proposes a Bitwise Gated Recurrent Unit (BGRU) network for the single-channel source separation task. Recurrent Neural Networks (RNN) require several sets of weights wit…