Hon Keung Kwan

University of Windsor — Canada

Computer Science · Physical Sciences

26h-index2.8kcitations311works1.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Digital Filter Design and Implementation(123), Advanced Adaptive Filtering Techniques(95), Image and Signal Denoising Methods(66), Neural Networks and Applications(51), Blind Source Separation Techniques(38)

Publications311 total

Tailoring the Crystallization Behavior of Mixed Lead‐Tin Mixed‐Halide Perovskites for Optimal‐Bandgap Solar Cells
Advanced Science·2025· 1 citedOpen Access
Multi-path Processing Structure for Multi-scale Feature Fusion in Speech Separation Transformer
Circuits Systems and Signal Processing·2025
MUFFIN-HGCN: Multi-Feature Fusion Hierarchical-GCN for 3D Object Detection
IEEE Transactions on Vehicular Technology·2025
Enhancing bone-conducted speech with spectrum similarity metric in adversarial learning
Speech Communication·2025· 1 cited
Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability
IEEE Transactions on Affective Computing·2024· 3 cited
Multi-scale 3D-CRU for EEG emotion recognition*
Biomedical Physics & Engineering Express·2024· 4 cited
Multi-Level Information Aggregation Based Graph Attention Networks Towards Fake Speech Detection
IEEE Signal Processing Letters·2024· 4 cited
Bipartite Graph Approximation by Eigenvalue Optimization
IEEE Transactions on Signal and Information Processing over Networks·2024· 1 cited
Multi-Granularity Prosodic Speech Synthesis with Grammar Information
SSRN Electronic Journal·2024Open Access
GraphSAGE-Based Dynamic Spatial–Temporal Graph Convolutional Network for Traffic Prediction
IEEE Transactions on Intelligent Transportation Systems·2023· 78 cited
A Novel Attention-Guided Generative Adversarial Network for Whisper-to-Normal Speech Conversion
Cognitive Computation·2023· 4 cited
Combating Uncertainty and Class Imbalance in Facial Expression Recognition
arXiv (Cornell University)·2022Open Access
Multi-Scale Feature Fusion Transformer Network for End-to-End Single Channel Speech Separation
arXiv (Cornell University)·2022· 1 citedOpen Access
Sparse to Dense: LiDAR Point Cloud Upsampling by Multi-modal GAN
TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)·2022· 3 cited
Attention-Based Accurate and Robust Facial Landmark Detector
TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)·2022
Combating Uncertainty and Class Imbalance in Facial Expression Recognition
TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)·2022· 4 cited
CycleGAN with Dual Adversarial Loss for Bone-Conducted Speech Enhancement
TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)·2022
A joint learning framework for Gaussian processes regression and graph learning
Signal Processing·2022· 14 cited
Kernel Regression for Matrix-Variate Gaussian Distributed Signals Over Sample Graphs
IEEE Transactions on Signal and Information Processing over Networks·2022· 1 cited
CycleGAN with Dual Adversarial Loss for Bone-Conducted Speech Enhancement
arXiv (Cornell University)·2021· 1 citedOpen Access
page 1 of 16Next →

Frequent Co-authors

Aimin Jiang(14), Yanping Zhu(5), C.Z. Tang(4), Yibin Tang(3), Felix Albu(3), C.L. Chan(3), Liang Tao(3), Swarna Bai Arniker(2), Sukanta Basu(2), Paul Henshaw(2), Nihar Biswas(2), Benjamin Y. M. Kwan(2), Jennifer Kwan(2), Yaling Cai(1), Tao Liu(1), Jia Zhou(1), Min Li(1), Jing Shang(1), Xiaofeng Liu(1), Changli Li(1)