3 papers
cs.SD2021
Lightweight Dual-channel Target Speaker Separation for Mobile Voice Communication
Yuanyuan Bao, Yanze Xu, Na Xu +7
Nowadays, there is a strong need to deploy the target speaker separation (TSS) model on mobile devices with a limitation of the model size and computational complexity. To better p…
cs.LG2021
A Coupled Random Projection Approach to Large-Scale Canonical Polyadic Decomposition
Lu-Ming Wang, Ya-Nan Wang, Xiao-Feng Gong +2
We propose a novel algorithm for the computation of canonical polyadic decomposition (CPD) of large-scale tensors. The proposed algorithm generalizes the random projection (RAP) te…
cs.SD2018
Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition
Ke Wang, Junbo Zhang, Sining Sun +3
We investigate the use of generative adversarial networks (GANs) in speech dereverberation for robust speech recognition. GANs have been recently studied for speech enhancement to…