Summary
Chenglin Xu is a postdoctoral researcher at the National University of Singapore with nine years of research experience in speech and audio processing, having completed a PhD in Computer Science at Nanyang Technological University. His work focuses on far-field speech recognition, beamforming, source separation, speaker extraction, multi-talker speaker verification and speech enhancement, blending deep learning with signal-processing techniques. He has a strong track record from thesis to applied projects, including developing a Malay sentence boundary detection system that combined prosodic DNN outputs with lexical CRF models. Based in Singapore, Chenglin brings cross-cultural training from Northwestern Polytechnical University in China to cutting-edge labs in Singapore, enabling practical solutions for noisy, multi-speaker environments. Colleagues value his ability to translate complex academic models into robust research prototypes aimed at real-world far-field speech problems.
9 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Nanyang Technological University
Master’s Degree, Computer Application Technology (Speech Processing), Master’s Degree, Computer Application Technology (Speech Processing) at Northwestern Polytechnic University (CN)
English, Chinese