no code implementations • 29 Nov 2023 • Yuhang Yang, Yizhou Peng, Xionghu Zhong, Hao Huang, Eng Siong Chng
The Mixed Error Rate results show that the amount of adaptation data may be as low as $1\sim10$ hours to achieve saturation in performance gain (SEAME) while the ASRU task continued to show performance with more adaptation data ($>$100 hours).
no code implementations • 18 Aug 2023 • Rui Ding, Jielong Yang, Feng Ji, Xionghu Zhong, Linbo Xie
To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction.
1 code implementation • 22 Feb 2023 • Yuchen Hu, Chen Chen, Heqing Zou, Xionghu Zhong, Eng Siong Chng
To alleviate this problem, we propose a novel network to unify speech enhancement and separation with gradient modulation to improve noise-robustness.
no code implementations • 28 Aug 2021 • Minjie Cai, Minyi Luo, Xionghu Zhong, Hao Chen
We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) the joint alignment of distributions for inputs (feature alignment) and outputs (self-training) is needed.