Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding
WASPAA, pp. 254-258, 2017.
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 iterative soft-thresholding algorithm (ISTA) that solves the optimization problem for sparse nonnegative matrix factorization (NMF) of spectrograms. We name this networ...More
Full Text (Upload PDF)
PPT (Upload PPT)