Papers published: EMNLP 2023 Findings, ICLR 2024, NeurIPS 2024, etc.; Awards: First place in DCASE 2024 Challenge Task6; Projects: Released multiple open-source projects including SpeechGPT, SpeechGPT2, SpeechTokenizer, and SpeechAlign.
Research Experience
Conducted research at FudanNLPLab, involved in multiple research projects such as the SpeechGPT series, SpeechTokenizer, and SpeechAlign.
Education
Master's student at Fudan University, supervised by Prof. Yaqian Zhou and Prof. Xipeng Qiu; B.S. degree from Fudan University, advised by Prof. Fuliang Weng; Interned at Bytedance AI Lab, mentored by Rong Ye.
Background
Research interests: End-to-end Voice Agent, Speech Foundation Models, and Multi-Modal LLM. Developed several foundation models for speech, including SpeechGPT, SpeechGPT2, SpeechTokenizer, and SpeechAlign.
Miscellany
Personal interests: Seeking Ph.D. and job opportunities worldwide, open to academic collaboration opportunities.