no code implementations • 29 Jun 2022 • Zheng Fang, Xiongwei Zhang, Tieyong Cao, Yunfei Zheng, Meng Sun
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.
no code implementations • 4 Feb 2021 • Gang Min, Xiongwei Zhang, Xia Zou, Xiangyang Liu
Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality.
no code implementations • 15 Sep 2020 • Linlin Zheng, Jiakang Li, Meng Sun, Xiongwei Zhang, Thomas Fang Zheng
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%.