DropFilterR: A Novel Regularization Method for Learning Convolutional Neural Networks
Sign Up to like & getrecommendations! Published in 2019 at "Neural Processing Letters"
DOI: 10.1007/s11063-019-10147-0
Abstract: The past few years have witnessed the fast development of regularization methods for deep learning models such as fully-connected deep neural networks (DNNs) and convolutional neural networks (CNNs). Part of previous methods mainly consider to… read more here.
Keywords: neural networks; method; convolutional neural; dropfilterr novel ... See more keywords
A novel regularization framework for transient noise reduction
Sign Up to like & getrecommendations! Published in 2018 at "Applied Acoustics"
DOI: 10.1016/j.apacoust.2017.07.020
Abstract: Abstract In this paper, we propose a novel method for estimating clean speech from a single channel transient noise corrupted speech. In the proposed method we assume that speech spectrogram is both sparse and has… read more here.
Keywords: novel regularization; transient noise; noise; noise reduction ... See more keywords