Chen Xie

Chen Xie is a faculty member in the Department of Computer Science at Shanghai Jiao Tong University. His research interests include deep learning, speech recognition, speech synthesis, and speech translation. He holds a bachelor's degree from Xiamen University (2005.9–2009.7), a master's degree from Tsinghua University (2009.9–2012.7), and a Ph.D. from the University of Cambridge (2012.9–2016.10). He served as a postdoctoral researcher at the University of Cambridge (2016.10–2017.12) and worked as a senior researcher at Microsoft Research (2021.9–present). He is affiliated with the Intelligent Voice Technology Laboratory.

Xie Chen is a researcher at Shanghai Jiao Tong University with expertise in Machine Learning, Speech Recognition, Speech Synthesis, and Speech&Audio Processing. Their work focuses on advancing deep neural networks for speech and pattern recognition, with applications in real-time streaming transformer transducer systems, efficient text-to-speech models, and self-supervised pre-training for speech emotion representation. Chen's research also explores domain-adaptive end-to-end speech recognition, noise robustness, and multimodal emotion recognition. They have developed tools like EAT and CUED-RNNLM for efficient language model training and evaluation. Their contributions span both theoretical and practical advancements in speech and audio processing technologies.