About me
Hi! I’m Baotong. I am a second-year Ph.D. student at the Audio and Information Research Lab, University of Rochester, NY, USA. I am fortunate to work with Prof. Zhiyao Duan. I received my B.E. Degree in Automation from Tsinghua University in 2024. I was also a member of the Tong(General Artificial Intelligence) class. I worked with Prof. Jiwen Lu in i-VisionGroup on explainable AI.
My research interests are in controllable and deployable audio intelligence, with the focus on both speech and music. Currently I’m working on streaming speech generation and performance music synthesis. I also have some interest in deep learning theory.
🔥 News
- 2026.06: The project which I participated as an audio enginner has been published by UR News Center!
- 2026.05: I joined Adobe as a Research Intern, working with Ke Chen, Yunyun Wang and Zeyu Jin!
- 2025.11: I attended SANE 2025 and presented the Conan paper!
- 2025.09: Thrilled to attend ISMIR 2025 as a volunteer!
- 2025.09: One paper accepted by ASRU 2025!
- 2025.07: I received a travel grant for ISMIR 2025!
- 2025.06: One paper accepted by Interspeech 2025!
Honors and Awards
- ISMIR Travel Grant, 2025
- Tsinghua Arts and Culture Merit Scholarship, 2021 & 2022
- Tsinghua Academic Excellence Award, 2022 & 2023
- Tsinghua Excellence in Science and Technology Innovation Award, 2023
🎼 Musical Experience
I have seven years of experience learning and playing the electric piano, from the age of 5 to 12, and I started learning acoustic guitar at the age of 13. Fortunately, I still practice guitar in my free time.
In addition, I started writing my own pop songs in high school and taught myself music arrangement and mixing in college to try to produce my compositions. I’ve been selected to join Tsinghua University’s Music Dream Programme for the Class of 2021-2022, which is designed to nurture and develop campus musicians. Currently, 7 songs I produced using logic pro are available online on various music platforms.
Links of my musician page: