Kai Wang

I am a MASc student and research assistant in Department of Eletrical Computer Engineering, Concordia University, under the supervision of Prof. Wei-Ping Zhu. I also worked on self-supervised learning and audio-visual learning, advised by Dr. Chao Xing, Dr. Anderson Avila, and Dr. Mehdi Rezagholizadeh as research intern in Huawei Noah’s Ark Laboratory, Montreal, Canada.

I obtained my bachelor's degree in Electrical and Information Engineering from North University of China.

Email  /  CV  /  LinKedIn  /  Github  /  Google Scholar

My research works focus on deep learning and its application to signal processing (speech, image and video), multi-modal learning, self-supervised learning. I am also quite interested in the applications of deep reinforcement learning such as communication network or social network.

Proposed cross-parallel transformer neural network to extract and dynamically fuse the local and global information of long-range speech sequences.

Proposed attention-free MLP architecture to achieve competitive performance compared with attention-based methods.

Incorporate transformer structure into encoder and decoder of UNet to solve the limited receptive field of the CNN structure

Proposed two-stage transformer neural network to extract local and global information of long-range speech feature.

Proposed context-aware UNet to extract contextual information of speech feature.

Conference reviewer: ISCAS 2021, NEWCAS 2021, NEWCAS 2022

This website is inspired by Jon Barron. Thanks!

(last update: Feb 2022)