My Photo

Tianxin Xie (谢添鑫)

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.

My research focuses on text-to-speech, speech LLMs, audio generation and reasoning, and multi-modal learning.

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

Navigation

News

  • 2025-11-10: I have started my internship at Tencent AI Lab.
  • 2025-11-08: One paper accepted by AAAI 2026.
  • 2025-08-21: One paper accepted by EMNLP 2025.
  • 2024-12-21: One paper accepted by ICASSP 2025.
  • 2024-12-13: One paper accepted by TPAMI.
  • 2024-12-09: We released a comprehensive survey of controllable speech synthesis on arXiv.
  • 2024-07-01: I graduated from the Institute of Computing Technology, Chinese Academy of Sciences, and will be pursuing my PhD at HKUST (GZ).

Publications

2025

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey EMNLP 2025
Tianxin Xie, Yan Rong, Pengfei Zhang, Wenwu Wang, Li Liu*
The 2025 Conference on Empirical Methods in Natural Language Processing
Paper Survey Repo
EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering arXiv 2025
Tianxin Xie, Shan Yang, Chenxing Li, Dong Yu, Li Liu*
arXiv preprint arXiv:2508.03543
Paper Code
Inter-and Intra-Sentence Cuer-Invariant Representation Learning for Generalizable Cued Speech Recognition ICASSP 2025
Tianxin Xie, Li Liu*
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Paper
Natural Adversarial Mask for Face Identity Protection in Physical World TPAMI 2025
Tianxin Xie, Hu Han*, Shiguang Shan, Xilin Chen
IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 47, Issue: 3, March 2025)
Paper Code

2024

Towards controllable speech synthesis in the era of large language models: A survey arXiv 2024
Tianxin Xie, Yan Rong, Pengfei Zhang, Wenwu Wang, Li Liu*
arXiv preprint arXiv:2412.06602
Paper Survey Repo