Tianxin Xie

my_photo.jpeg

I am a PhD student at the AI Thrust, Information Hub, Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Li Liu. I received my B.E. degree in Computer Science from Hunan Normal University, and my M.S. degree in Computer Science from the University of Chinese Academy of Sciences, advised by Prof. Hu Han. I also had the privilege of working closely with Prof. Shiguang Shan and Prof. Xilin Chen.

My research focuses on text-to-speech, speech LLMs, audio generation and reasoning, and physical AI.

Email: txie151[at]connect.hkust-gz.edu.cn / tianxin.xie[at]outlook.com

Google Scholar Semantic Scholar ORCID GitHub

news

Jul 17, 2026 One paper, i.e., PhyAVBench, is accepted at ACM MM 2026.
Jun 04, 2026 Three papers accepted at Interspeech 2026.
May 01, 2026 One paper accepted at ICML 2026.
Apr 13, 2026 We have released a T2AV benchmark, i.e., PhyAVBench, which contains 11,605 newly recorded videos. The dataset will be soon released to the public. The embeddings of audio samples and evaluation scripts have been released: https://github.com/imxtx/PhyAVBench.
Jan 27, 2026 One paper accepted at ICLR 2026.
Nov 10, 2025 I started my internship at Tencent AI Lab.
Nov 08, 2025 One paper accepted at AAAI 2026.
Aug 21, 2025 One paper accepted at EMNLP 2025.
Dec 21, 2024 One paper accepted at ICASSP 2025.
Dec 13, 2024 One paper accepted for publication in IEEE TPAMI.
Dec 09, 2024 We released a comprehensive survey of controllable speech synthesis on arXiv.
Jul 01, 2024 I graduated from the Institute of Computing Technology, Chinese Academy of Sciences, and will be pursuing my PhD at HKUST (GZ).

latest posts

selected publications

  1. arXiv
    SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows
    Tianxin Xie, Pengfei Zhang, Kai Jiang, Zelin Zhao, and Li Liu
    arXiv preprint arXiv:2609.34648, 2026
    PDF Code Website
  2. ACM MM 2026 (Oral)
    PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation CCF-A
    Tianxin Xie, Wentao Lei, Kai Jiang, Guanjie Huang, Pengfei Zhang, Chunhui Zhang, Fengji Ma, Haoyu He, Han Zhang, Jiangshan He, Jinting Wang, Linghan Fang, Lufei Gao, Orkesh Ablet, Peihua Zhang, Ruolin Hu, Shengyu Li, Weilin Lin, Xiaoyang Feng, Xinyue Yang, Yan Rong, Yanyun Wang, Zihang Shao, Zelin Zhao, Chenxing Li, Shan Yang, Wenfu Wang, Meng Yu, Dong Yu, and Li Liu
    In Proceedings of the 34th ACM International Conference on Multimedia, 2026
    PDF Code Website
  3. Interspeech 2026 (Oral)
    VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation
    Tianxin Xie, Chenxing Li, Dong Yu, and Li Liu
    In Interspeech 2026, 2026
    PDF Website
  4. EMNLP 2025
    Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey
    Tianxin Xie, Yan Rong, Pengfei Zhang, Wenwu Wang, and Li Liu
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    DOI PDF Code
  5. arXiv
    EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
    Tianxin Xie, Shan Yang, Chenxing Li, Dong Yu, and Li Liu
    arXiv preprint arXiv:2508.03543, 2025
    PDF
  6. ICASSP 2025
    Inter- and Intra-Sentence Cuer-Invariant Representation Learning for Generalizable Cued Speech Recognition
    Tianxin Xie and Li Liu
    In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
    DOI PDF
  7. TPAMI
    Natural Adversarial Mask for Face Identity Protection in Physical World CCF-A
    Tianxin Xie, Hu Han, Shiguang Shan, and Xilin Chen
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
    DOI PDF Code

Services

Conference Reviewer

  • The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025, 2026, 2027
  • The AAAI Conference on Artificial Intelligence (AAAI), 2026
  • The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
  • The International Conference on Learning Representations (ICLR), 2026, 2027
  • The ACM International Conference on Multimedia (MM), 2026
  • The National Conference on Man-Machine Speech Communication (NCMMSC), 2026

Journal Reviewer

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2026
  • ACM Computing Surveys (CSUR), 2026
  • Pattern Recognition (PR), 2025