Search Results for author:
Found 3 papers, 0 papers with code
A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
Comprehensive experimental results and analysis reveals that 1) the most widely used human natural skeleton structure adjacency matrix is unsuitable in skeleton-based action recognition; 2) The proposed adjacency matrix is superior in model performance, noise robustness and transferability.
Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach
Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality.
When Automatic Voice Disguise Meets Automatic Speaker Verification
The proposed approach generalizes well to restore the disguise with nonlinear frequency warping in VTLN by reducing its EER from 34. 3% to 18. 5%.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
