Hi, I’m Qingyu Liu (刘庆宇). I am currently a Master of Science in Engineering (MSE) student in Electrical and Computer Engineering (ECE) at Johns Hopkins University, where I am affiliated with the Smile Lab at the Center for Language and Speech Processing (CLSP) under the mentorship of Prof. Berrak Sisman. I also work as a remote research assistant at Shanghai Jiao Tong University X-LANCE Lab under the mentorship of Prof. Xie Chen. I completed my undergraduate studies at Shanghai Normal University under the mentorship of Prof. Yanhua Long.

My research interests are in speech, generative models, machine learning, and deep learning. Currently, I focus on:

• Speech Synthesis (Text to Speech)

I’m a Manchester United fanatic, and my dream is to see them conquer the Premier League once more. Feel free to reach out if you want to talk footy!

Education

• 2025.08 - present: Master of Science in Engineering (MSE) in Electrical and Computer Engineering at Johns Hopkins University.
  • GPA: 3.88/4.0
• 2020.10 - 2024.06: Bachelor’s degree in Electronic Information Engineering at Shanghai Normal University.
  • GPA: 3.95/4.0
  • Rank: 2/523 (Top 0.5%)
  • TOEFL iBT: 104

Intern

• 2026.06 - present: Research Intern at Tencent Hunyuan.
• 2025.12 - present: Research Assistant in the Smile Lab at Center for Language and Speech Processing (CLSP).
• 2024.08 - present: Research Assistant in the Cross Media (X-)Language Intelligence Lab at Shanghai Jiao Tong University.

Publications

(* represents co-first authors, † represents corresponding authors)

2026

• Rixi Xu*, Qingyu Liu*, Haitao Li, Yushen Chen, Zhikang Niu, Yunting Yang, Jian Zhao, Ke Li, Berrak Sisman, Qinyuan Cheng, Xipeng Qiu, Kai Yu and Xie Chen†. “X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning.” arXiv preprint arXiv:2605.05611, 2026.
  

• Qingyu Liu, Yushen Chen, Zhikang Niu, Chuihui Wang, Yunting Yang, Bowen Zhang, Pengcheng Zhu, Jian Zhao, Kai Yu and Xie Chen†. “Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis.” ICASSP 2026.
  

• Qingyu Liu, Longfei Song, Dongxing Xu and Yanhua Long†. “ICSD: An Open-source Dataset for Infant Cry and Snoring Detection.” Journal of the Audio Engineering Society.
  

2023

• Qingyu Liu, Li Li, Yifan Zhou, Dongxing Xu and Yanhua Long†. “A Comparative Study of Deep Learning Methods for Infant Cry Detection.” NCMMSC 2023.
  

Honors and Awards

• 2024: Outstanding Graduate, Shanghai Normal University.
• 2024: 14th Challenge Cup, Silver Award.
• 2024: China International College Students’ Innovation Competition, Silver Award.
• 2024: 9th “Think Youth” Digital Creation, Innovation & Entrepreneurship Competition, First Prize in the Finals.
• 2024: National Undergrad Training Program for Innovation and Entrepreneurship, Project Leader.