Wei Fang

Wei Fang

Auto-generated profile, based on publicly available information

Wei Fang

Pharmaceutical Department, Chongqing University Three Gorges Hospital, Chongqing University, Chongqing 404100, P. R. China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 November 2023 in Organic Letters
Verified
Journal Article
Closed access
XFXianfu Fang
Xianfu Fang
TZTianyang Zhang
Tianyang Zhang
WFWei Fang
Wei Fang
GZGong Zhang
Gong Zhang
YLYangfeng Li
Yangfeng Li
YLYizhou Li
Yizhou Li

26 April 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
CLChia-Hsuan Lee
Chia-Hsuan Lee
HLHung-Yi Lee
Hung-Yi Lee
SWSzu-Lin Wu
Szu-Lin Wu
CLChi-Liang Liu
Chi-Liang Liu
WFWei Fang
Wei Fang
BTBo-Hsiang Tseng
Bo-Hsiang Tseng
Although multimedia or spoken content presents more attractive information than plain text content, the former is more difficult to display on a screen and be selected by a user. As a result, for humans, accessing large collections of spoken content is much more difficult and time-consuming than doing so for text content. It would therefore be helpful to develop machines which understand spoken content. In this paper, we propose two new tasks for machine comprehension of spoken content. The first is a listening comprehension test for TOEFL, a challenging academic English examination for English learners whose native languages are not English. We show that the proposed model outperforms the naive approaches and other neural network based models by exploiting the hierarchical structures of natural languages and the selective power of attention mechanism. For the second listening comprehension task - spoken SQuAD - we find that speech recognition errors severely impair machine comprehension; we propose the use of subword units to mitigate the impact of these errors.

13 October 2022
Verified
Conference Paper
Closed access
Jingwei MaJingwei Ma
Jingwei Ma
WFWei Fang
Wei Fang
CMCao Ming
Cao Ming
Kalman Filter and Extended Kalman Filter (EKF) have been widely applied for aero engine performance assessment. Aiming at improving upon the Kalman Filter based methods, this investigation explores applying Unscented Kalman Filter (UKF) algorithm for aero engine performance degradation evaluation. Improvements on the UKF algorithm are made for optimal performance, by adding a factor or adjusting the prediction variance matrix, as well as finding the optimal distribution of Sigma points. The simulation result shows that compared with EKF algorithm and with multi-dimensional degradation, the UKF algorithm proposed in this study improves the performance degradation assessment error by a large margin(33%), while suffering from prolonged numerical time and sensitivity to the initial error.

15 July 2013 in Information Technology Journal
Verified
Journal Article
Closed access
FWFang Wei
Fang Wei
WZWen Xue Zhi
Wen Xue Zhi
XJXu Jiang
Xu Jiang