About Me

I am currently a Master of Engineering (by Research) student at the College of Computing and Data Science, Nanyang Technological University (NTU), supervised by Prof. Eng Siong Chng. I received my Bachelor’s degree in Data Science from Duke University and Duke Kunshan University in 2025, supervised by Prof. Ming Li. I am broadly interested in speech processing, AI security, and multimodal learning. Specifically, my research focuses on audio deepfake detection, audio watermarking, sound event detection, and language identification.

Publications

• 2026 Interspeech Oral VoxWatermark: A Large-Scale Benchmark for Audio Watermark Detection under Perturbations | Farnaz Sedaghati*, Yuxi Wang*, Zicheng Weng, Wei Rao | [paper] [code]
• 2025 Interspeech VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset | Yuxi Wang*, Yikang Wang*, Qishan Zhang, Hiromitsu Nishizaki, Ming Li | [paper] [page] [code] [space]
• 2025 APSIPA Efficient Video to Audio Mapper with Visual Scene Detection | Mingjing Yi, Yuxi Wang, Ming Li | [paper] [page] [code]

Educations

• 2025.08 - 2027.05 (expected) Nanyang Technological University Singapore
  • Master of Engineering (by Research), College of Computing and Data Science
  • Supervisor: Prof. Eng Siong Chng, Speech and Language Laboratory
• 2021.08 - 2025.05 Duke Kunshan University China & United States
  • Bachelor of Science in Data Science
  • Supervisor: Prof. Ming Li, Speech and Multimodal Intelligent Information Processing (SMIIP) Lab

Intern Experiences

• 2026.02 - 2026.07 Huawei Research Center Singapore
  • Research Intern, Digital Trust Lab, Vienna 2012 Laboratory
  • Mentor: Dr. Lei Wang
  • Working on audio deepfake.

Academic Services

• Conference reviewer for ICASSP 2026.