Hi, I'm Pei-Chun Chang. I’m an AI Engineer at Novatek Microelectronics Corp., where I focus on real-time speech separation and audio machine learning for edge devices. I completed my Ph.D. in Computer Science at National Yang Ming Chiao Tung University in 2024. My work bridges academic research and practical AI applications, with a focus on audio and speech processing, digital image/signal processing, music information retrieval, machine learning, and deep learning. I continue to engage in academic research, applying my knowledge to build efficient, deployable AI systems. Outside of work, I enjoy exploring new AI techniques and developing projects that combine research with real-world impact.

Advances in Intelligent Information Hiding and Multimedia Signal Processing: Proceedings of the 20th IIHMSP, 2026

2025 Thirteenth International Symposium on Computing and Networking (CANDAR'25)

Pattern Recognition (PR), 2024

2022 International Joint Conference on Neural Networks (IJCNN'22)

International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2022

2021 International Conference on Multimedia Retrieval (ICMR'21)

[code repository]

2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'21)

2020 Asian Conference on Computer Vision (ACCV'20)

[code repository]

2018 3rd International Conference on Computer and Communication Systems (ICCCS)

IEEE Transactions on Multimedia (Volume: 20, Issue: 12, Dec. 2018)

2016 World Conference on Innovation, Engineering, and Technology (IET)

Speech separation

Music gerne/emotion classification

Birdsong recognition

Face recognition

Perceptual content reconstruction using brain signals

Stroke segmentation

Department of Computer Science

Department of Computer Science

Computer Science and Information Engineering

Computer Science and Information Engineering