My research focuses on building more natural and adaptive human–AI interactions through speech and language. I am particularly interested in how conversational systems can better understand their users and communicate in more expressive and human-like ways. My current work includes user modeling, expressive speech generation, and Speech Language Models (SLMs).
Research interests
Speech Language Models
Expressive Speech
User Modeling
Experience
Tencent Multimedia Lab2025.07–Present
Research Intern · Speech Language Model Group
Text data preparation for continual pre-training of Speech Language Models.
News
Preprint · 2026.06
Released the revised SASLM preprint on expressive speech generation through self-aware intent–realization alignment. arXiv ↗
Preprint · 2026.02
Released DDTSR, a discourse-aware dual-track framework for low-latency spoken dialogue systems. arXiv ↗
@article{wang2026bridging,month=apr,title={Bridging What the Model Thinks and How It Speaks:
Expressive Speech Generation via Self-Aware
Intent-Realization Alignment},author={Wang, Kuang and Wei, Lai and Lin, Ping and Bai, Qibing and Fang, Wenkai and Zhou, Li and Jiang, Feng and Jiang, Zhongjie and Huang, Jun and Wang, Yannan and Li, Haizhou},journal={arXiv preprint arXiv:2604.11424},year={2026},}
@inproceedings{wang2025know,month=jul,title={Know You First and Be You Better: Modeling Human-Like
User Simulators via Implicit Profiles},author={Wang, Kuang and Li, Xianfei and Yang, Shenghao and Zhou, Li and Jiang, Feng and Li, Haizhou},booktitle={Proceedings of the 63rd Annual Meeting of the
Association for Computational Linguistics},year={2025},}
@article{jiang2024bridging,month=jan,title={Bridging Research and Readers: A Multi-Modal Automated
Academic Papers Interpretation System},author={Jiang, Feng and Wang, Kuang and Li, Haizhou},journal={arXiv preprint arXiv:2401.09150},year={2024},}
@article{wang2026bridging,month=apr,title={Bridging What the Model Thinks and How It Speaks:
Expressive Speech Generation via Self-Aware
Intent-Realization Alignment},author={Wang, Kuang and Wei, Lai and Lin, Ping and Bai, Qibing and Fang, Wenkai and Zhou, Li and Jiang, Feng and Jiang, Zhongjie and Huang, Jun and Wang, Yannan and Li, Haizhou},journal={arXiv preprint arXiv:2604.11424},year={2026},}
@inproceedings{ke2026catch,month=mar,title={CATCH: A Controllable Theme Detection Framework with
Contextualized Clustering and Hierarchical Generation},author={Ke, Rui and Xu, Jiahui and Yang, Shenghao and Wang, Kuang and Jiang, Feng and Li, Haizhou},booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},year={2026},doi={10.1609/aaai.v40i37.40406},volume={40},number={37},pages={31419--31428},}
@article{liu2026discourse,month=feb,title={Discourse-Aware Dual-Track Streaming Response for
Low-Latency Spoken Dialogue Systems},author={Liu, Siyuan and Xu, Jiahui and Jiang, Feng and Wang, Kuang and Zhao, Zefeng and Huang, Chu-Ren and Gu, Jinghang and Yin, Changqing and Li, Haizhou},journal={arXiv preprint arXiv:2602.23266},year={2026},}
@inproceedings{wang2025know,month=jul,title={Know You First and Be You Better: Modeling Human-Like
User Simulators via Implicit Profiles},author={Wang, Kuang and Li, Xianfei and Yang, Shenghao and Zhou, Li and Jiang, Feng and Li, Haizhou},booktitle={Proceedings of the 63rd Annual Meeting of the
Association for Computational Linguistics},year={2025},}
@article{jiang2024bridging,month=jan,title={Bridging Research and Readers: A Multi-Modal Automated
Academic Papers Interpretation System},author={Jiang, Feng and Wang, Kuang and Li, Haizhou},journal={arXiv preprint arXiv:2401.09150},year={2024},}
