About me

I am a Ph.D. student in Electrical Engineering and Computer Science (EECS) at National Taiwan University (NTU), where I working with Prof. Hung-yi Lee and Prof. Jyh-Shing Roger Jang. I received M.S. degree from NTU in 2023 and B.S. degree from Taiwan Tech in 2020. My research interests include, but are not limited to, speech processing and machine learning. I'm honored to receive Google Student Travel Grant in 2024.

Selected Publications (* equal contribution)

[11] Xuanjun Chen*, Shih-Peng Cheng*, Jiawei Du, Lin Zhang, Xiaoxiao Miao, Chung-Che Wang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang. "Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling," in arxiv 2025.
arXiv

[10] Xuanjun Chen, Chia-Yu Hu, I-Ming Lin, Yi-Cheng Lin, I-Hsiang Chiu, You Zhang, Yi-Hsuan Yang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang, "How Does Instrumental Music Help SingFake Detection?" to appear in arXiv 2025.

[9] Xuanjun Chen*, I-Ming Lin*, Lin Zhang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang. "Towards Generalized Source Tracing for Codec-Based Deepfake Speech," in IEEE ASRU 2025.
arXiv / Code

[8] Xuanjun Chen, I-Ming Lin, Lin Zhang, Jiawei Du, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang. "Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy," in INTERSPEECH 2025.
arXiv / Code

[7] Xuanjun Chen, Jiawei Du, Haibin Wu, Lin Zhang, I-Ming Lin, I-Hsiang Chiu, Wenze Ren, Yuan Tseng, Yu Tsao, Jyh-Shing Roger Jang, Hung-yi Lee, "CodecFake+: A Large-Scale Neural Audio Codec-Based Deepfake Speech Dataset," Preprint, 2025.
arXiv

[6] Xuanjun Chen, Haibin Wu, Chung-Che Wang, Hung-yi Lee, and Jyh-Shing Roger Jang, "Multimodal Transformer Distillation for Audio-Visual Synchronization," in ICASSP 2024.
IEEE / arXiv / Code / Poster

[5] Xuanjun Chen, Haibin Wu, Jyh-Shing Roger Jang, and Hung-yi Lee. "Singing Voice Graph Modeling for SingFake Detection," in INTERSPEECH 2024 (Oral).
ISCA / arXiv / Code / Lightning Talk

[4] Xuanjun Chen*, Jiawei Du*, Haibin Wu, Jyh-Shing Roger Jang, and Hung-yi Lee. "Neural Codec-based Adversarial Sample Detection for Speaker Verification," in INTERSPEECH 2024.
ISCA / arXiv / Code / Poster

[3] Jiawei Du, I-Ming Lin, I-Hsiang Chiu, Xuanjun Chen, Haibin Wu, Wenze Ren, Yu Tsao, Hung-yi Lee, Jyh-Shing Roger Jang. "DFADD: The Diffusion and Flow-Matching based Audio Deepfake Dataset," in IEEE SLT 2024.
IEEE / arXiv / Code / Huggingface

[2] Xuanjun Chen*, Haibin Wu*, Helen Meng, Hung-yi Lee, and Jyh-Shing Roger Jang, "Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection," in IEEE SLT 2022, Jan 2023.
IEEE / arXiv / Demos / Poster / Video

[1] Xuanjun Chen*, Yen-Lun Liao*, Chung-Che Wang, and Jyh-Shing Roger Jang, "Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification," in ISCA SPSC 2022, Sept 2022.
ISCA / arXiv

Selected Honors

2025: National Science and Technology Council Conference Subsidy

2024: Google Student Travel Grant, Google LLC

2024: CTCI Foundation Bursary Award for Overseas Students

2020-25: (5x) Kwong Tung Community Outstanding Student Scholarship

2021: Ranked 3rd/42 teams in LA track of ASVspoof 2021 challenge

2018-20: Certificate of Achievement, Taiwan Tech (Top 5%, 3 semesters)

2016: National Encouragement Scholarship, Ministry of Education

Selected Serivces

2023-Now: Reviewer: AAAI, ACL, EMNLP, ICASSP, INTERSPEECH, COLING, MLSP, IJPRAI, IALP, ECCV AVGenL

2023-Now: Admin Assistant, NVIDIA-NTU AI Joint Innovation Center, NTU

2025: Co-Organizer, Responsible Speech & Audio Generative AI, ASRU'25

2024: Technical Committee, Codec-SUPERB Challenge, IEEE SLT 2024

2024-25: Teaching Assistant, EE5200: Introduction to Generative AI (2024 Spr.) and EE5184: Machine Learning (2025 Spr.), NTU