Hi, I am Yuankun Xie, a postdoctoral researcher in the Department of Electrical and Electronic Engineering at The Hong Kong Polytechnic University. I received my Ph.D. in Information and Communication Engineering from the Communication University of China, and was jointly trained at the Institute of Automation, Chinese Academy of Sciences.

My research focuses on audio deepfake detection, audio large language models (ALLMs), domain generalization, out-of-distribution detection, and neural audio codecs. I have published 30+ papers, including 15 first author papers, in leading speech and audio conferences and journals such as TIFS, TASLP, AAAI, ACM MM, ICASSP, and INTERSPEECH. I am interested in research collaborations on trustworthy speech and audio intelligence. Please feel free to contact me at xieyuankun@cuc.edu.cn.

🔥 News

2026.07: 👓 Joined Professor Kong Aik Lee’s group at The Hong Kong Polytechnic University as a postdoctoral researcher.
2026.04: 🚀 Organizing the AT-ADD Grand Challenge at ACM Multimedia 2026.
2026.01: 🎉 2 papers accepted by ICASSP 2026.
2025.11: 🎉 1 paper accepted by AAAI 2026.
2025.11: 💻 Ranked 1st place in both Track 1 and Track 2 of the ESDD Competition.
2025.07: 💻 Ranked 3rd in Track 3 of the Alibaba Tianchi 2025 Global AI Attack and Defense Challenge.
2024.12: 🎉 1 journal paper accepted by IEEE/ACM TASLP.
2024.09: 🌏 Attended INTERSPEECH 2024 in Greece, presenting one poster and one oral presentation.
2024.08: 🎉 1 paper accepted by INTERSPEECH 2024 Workshop (ASVspoof 5).
2024.08: 🎉 3 papers accepted by ISCSLP 2024.
2024.06: 🎉 4 papers accepted by INTERSPEECH 2024.
2024.04: 🌏 Attended ICASSP 2024 in Korea, presenting one poster and one oral presentation.
2024.01: 🎉 2 papers accepted by ICASSP 2024.
2023.11: 👓 Joined Professor Jianhua Tao’s group at the Institute of Automation, Chinese Academy of Sciences for joint Ph.D. training, under the guidance of Dr. Ruibo Fu.
2023.10: 🎉 1 journal paper accepted by IEEE TIFS.
2023.08: 🌏 Attended the IJCAI 2023 DADA Workshop (ADD 2023) in Macao and delivered one presentation.
2023.06: 🎉 2 papers accepted by INTERSPEECH 2023 and the IJCAI 2023 DADA Workshop.
2023.05: 💻 Ranked 6th/14 in Track 1.1, 5th/52 in Track 1.2, and 6th/17 in Track 2 of the ADD 2023 Competition.
2022.09: 👓 Joined Professor Long Ye’s group at the Communication University of China, under the guidance of Dr. Haonan Cheng.

📝 First Author Publications

† indicates that I am the co-first author listed second. For the complete and latest publication list, please visit my Google Scholar profile.

Journal

TIFS 2024 · SCI Zone 1 · CCF A: Domain Generalization Via Aggregation and Separation for Audio Deepfake Detection. [paper]

Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye
TASLP 2025 · SCI Zone 1 · CCF B: The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio. [paper] [code]

Yuankun Xie, Yi Lu, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Jianhua Tao, Xin Qi, Xiaopeng Wang, Yukun Liu, Haonan Cheng, Long Ye, Yi Sun
Neurocomputing 2026 · SCI Zone 2 · CCF C: Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition. [preprint] [code]

Yuankun Xie, Xiaopeng Wang, Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Songjun Cao, Long Ma, Chenxing Li, Haonan Cheng, Long Ye

Conference

ACM MM 2026 · CCF A: AT-ADD: All-Type Audio Deepfake Detection Challenge Summary. [website]

Yuankun Xie, Haonan Cheng, Jiayi Zhou, Xiaoxuan Guo, Tao Wang, Changhao Zhang, Jian Liu, Weiqiang Wang, Ruibo Fu, Xiaopeng Wang, Hengyan Huang, Xiaoying Huang, Long Ye, Guangtao Zhai
AAAI 2026 · CCF A: Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception. [paper] [code]

Yuankun Xie, Ruibo Fu, Zhiyong Wang, Xiaopeng Wang, Songjun Cao, Long Ma, Haonan Cheng, Long Ye
IJCAIW 2023 · CCF A: Single Domain Generalization for Audio Deepfake Detection. [paper]

Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye
ICASSP 2026 · CCF B: Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform. [paper]

Yuankun Xie, Ruibo Fu, Xiaopeng Wang, Zhiyong Wang, Ya Li, Zhengqi Wen, Haonan Cheng, Long Ye
INTERSPEECH 2024 W (ASVspoof 5) · CCF B: Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof 5 Deepfake Challenge. [paper]

Yuankun Xie, Xiaopeng Wang, Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Haonan Cheng, Long Ye
INTERSPEECH 2024 · CCF B: Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy. [paper] [code]

Yuankun Xie, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Xiaopeng Wang, Haonan Cheng, Long Ye, Jianhua Tao
INTERSPEECH 2024 · CCF B: Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio. [paper] [code]

Yi Lu†, Yuankun Xie†, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Zhiyong Wang, Xin Qi, Xuefei Liu, Yongwei Li, Yukun Liu, Xiaopeng Wang, Shuchen Shi
ICASSP 2024 · CCF B: An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection. [paper] [code]

Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye
ICASSP 2024 · CCF B: FSD: An Initial Chinese Dataset for Fake Song Detection. [paper] [code]

Yuankun Xie, Jingjing Zhou, Xiaolin Lu, Zhenghao Jiang, Yuxin Yang, Haonan Cheng, Long Ye
INTERSPEECH 2023 · CCF B: Learning a Self-Supervised Domain-Invariant Feature Representation for Generalized Audio Deepfake Detection. [paper]

Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye
ICME 2023 · CCF B: Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis. [paper]

Yutian Wang†, Yuankun Xie†, Kun Zhao, Hui Wang, Qin Zhang
ISCSLP 2024: Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio? [paper] [code]

Yuankun Xie, Chenxu Xiong, Xiaopeng Wang, Zhiyong Wang, Yi Lu, Xin Qi, Ruibo Fu, Yukun Liu, Zhengqi Wen, Jianhua Tao, Guanjun Li, Long Ye

Under Review

AAAI 2027 · Under review · CCF A: Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning. [preprint]

Yuankun Xie, Xiaoxuan Guo, Jiayi Zhou, Tao Wang, Jian Liu, Ruibo Fu, Xiaopeng Wang, Haonan Cheng, Long Ye
AAAI 2027 · Under review · CCF A: Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection. [preprint]

Xiaoxuan Guo†, Yuankun Xie†, Haonan Cheng, Jiayi Zhou, Jian Liu, Hengyan Huang, Long Ye, Qin Zhang
TMM · Under review · SCI Zone 1 · CCF A: AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection. [website]

Yuankun Xie, Haonan Cheng, Jiayi Zhou, Xiaoxuan Guo, Tao Wang, Changhao Zhang, Jian Liu, Weiqiang Wang, Ruibo Fu, Xiaopeng Wang, Hengyan Huang, Xiaoying Huang, Long Ye, Guangtao Zhai

🏢 Research Experience

2026.07 - present Postdoctoral Researcher, The Hong Kong Polytechnic University (Hong Kong)
- Department of Electrical and Electronic Engineering; advised by Professor Kong Aik Lee.
2025.10 - 2026.06 Research Intern, Ant Group (Beijing, China)
- Worked on interpretable all-type audio deepfake detection with audio LLMs and the AT-ADD challenge.
2025.06 - 2025.08 Research Intern, ByteDance (Beijing, China)
- Worked on first-order ambisonic spatial-audio synthesis from 360-degree video and spatial-audio captions.
2024.11 - 2025.04 Research Intern, Tencent YouTu Lab (Beijing, China)
- Worked on in-the-wild speech deepfake detection, neural-codec source tracing, and all-type audio deepfake detection.
2023.09 - 2024.11 Research Intern, Tsinghua Qiyuan Lab (Beijing, China)
- Worked on robust audio deepfake detection, partial-fake localization, and open-set source tracing.

💻 Competitions and Challenges

2026 Organizer, ACM MM 2026 AT-ADD All-Type Audio Deepfake Detection Challenge.
2026 ICASSP 2026 Environmental Sound Deepfake Detection Challenge: 1st/24 in Track 1 and 1st/15 in Track 2.
2026 ICME 2026 ESDD2 Environmental Sound Deepfake Detection Challenge: 2nd/15.
2025 Alibaba Tianchi Global AI Attack and Defense Challenge, Audio Deepfake Track: 1st/360 in the preliminary round and 3rd/360 in the final.
2024 ASVspoof 5 Deepfake Detection Challenge, Progress set: 2nd/48.
2024 The 9th FinVolution Global Data Science Competition, Deepfake Speech Detection: 2nd/202 in the preliminary round and 8th/30 in the final.
2023 Audio DeepFake Detection Challenge, Track 1.2: 5th/52.

Yuankun Xie