Jeff Chan-Jan Hsu (許湛然)

I am an incoming Ph.D. student at the Language Technologies Institute, Carnegie Mellon University, where I will join the Multimodal Speech Processing (MSP) Laboratory advised by Professor Carlos Busso. Before joining CMU, I worked at MediaTek Research as a Research Scientist, working on large language models and spoken systems. I received my master’s degree from National Taiwan University, where I conducted research at the NTU Speech Lab under the supervision of Professor Hung-Yi Lee and Professor Yu Tsao.

Selected Publications

• Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR
  Chan-Jan Hsu, Yi-Chang Chen, Feng-Ting Liao, Pei-Chen Ho, Yu-Hsiang Wang, Po-Chun Hsu, Da-shan Shiu
  Findings of ACL 2025 [paper] [code]
• A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
  Cheng-Kang Chou*, Chan-Jan Hsu*, Ho-Lam Chung, Liang-Hsuan Tseng, Hsi-Chun Cheng, Yu-Kuan Fu, Kuan-Po Huang, Hung-Yi Lee
  ASRU 2025 [paper]
• T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5
  Chan-Jan Hsu, Ho-Lam Chung, Hung-Yi Lee, Yu Tsao
  ICASSP 2023 [paper]