Published multiple papers in international conferences such as ACL, ICASSP, and INTERSPEECH; received the 2025 IEEE Ganesh N. Ramaswamy Memorial Student Grant; co-authored a survey on Next Token Prediction Towards Multimodal Intelligence.
Research Experience
Currently a Research Scientist at ByteDance Seed; previously a Research Intern at Microsoft Research Asia, working on language modeling for speech synthesis and integrating speech with large language models.
Education
Ph.D., The Chinese University of Hong Kong, Human-Computer Communications Laboratory (HCCL), supervised by Prof. Helen Meng; M.Phil., Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Jie Tian; B.Sc., Harbin Institute of Technology (HIT).
Background
Research interests include language modeling for speech synthesis and the integration of speech with large language models. Also working on speech processing and recognition.