About me

I’m a third year ECE PhD candidate in UIUC SiNRG advised by Professor Romit Roy Choudhury. In general my area is signal processing and data science. My interest is to find the best world between classic signal processing and the current state of deep learning. I believe signal models would create a more explanable and efficient foundation for today’s machine learning models.

On the application side, I mostly worked on microphone array speech processing and audio-visual speech processing (enhancement, dereverberatin, separation, compressive coding). I’m very much into the concept of mixed reality. One example is our Earable Computing aiming for acoustics augmented reality.

I also work with Professor Mark Hasegawa-Johnson if any project is related to speech.

Education

• 2018-2021: B.S. in Computer Engineering, University of Illinois Urbana-Champaign
• 2021-current: MS/PhD in ECE, University of Illinois Urbana-Champaign

Work Experience

• 2022 Summer: Research Intern @ Tencent Ethereal Lab, Shenzhen, China
  • Mentored by the Great Researchers Yupeng shi, Wenzhe Liu, and Wei Xiao, working on efficient single channel speech enhancement (signal model based)
• 2023 Summer: Research Intern @ Tencent AI Lab, Bellevue, US
  • Mentored by the Great Researchers Yong Xu, Vinay Kothapally, and Dong Yu, working on multi-channel spatial speech coding and simultaneous neural beamforming and coding for noisy speech
• 2023 Fall: Research Intern @ Meta Reality Lab, Redmond, US
  • Mentored by the Great Researchers Ali Aroudi, Ke Tan, Ashutosh Pandey, Buye Xu, Francesco Nesto, and Jung-Suk Lee, project confidential for now…