Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding

WASPAA, pp. 254-258, 2017.

Cited by: 10|Bibtex|Views45|DOI:https://doi.org/10.1109/waspaa.2017.8170034
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments