I am a Ph.D. student at Shanghai Jiao Tong University (SJTU), advised by Prof. Yanmin Qian. My research is centered on building intelligent systems that can holistically understand, translate, and generate human speech. I am particularly interested in creating seamless, expressive, and real-time cross-lingual communication, exploring topics in end-to-end speech translation, controllable speech synthesis, and multimodal emotion recognition. I have published several papers at leading international conferences in the fields of speech and artificial intelligence as first-author.
Beyond my academic work, I am passionate about translating cutting-edge research into real-world applications. I have interned at Microsoft, Honor, and YSYB. At Honor, I played a key role in the successful launch of their on-device speech large model. I was also one of the main R&D members for the Luna-1, a pioneering multimodal emotion large model developed at YSYB.
Education
- 2023 - : PhD student, School of Computer Science, Shanghai Jiao Tong University
- 2019 - 2023: Bachelor of Engineering, Shanghai Jiao Tong University, Major in Computer Science and Technology
- 2016 - 2019: Shanghai High School, Math Specialty Class