LI, Xiang
POSITION/TITLE
SRIBD Associate Research Fellow
RESEARCH FIELD
Speech Language models; Speech-based interaction; Industrial Multi-agent systems.
lixiang@sribd.cn
PERSONAL WEBSITE
https://scholar.google.com/citations?user=ExHb3vwAAAAJ&hl=zh-CN
EDUCATION BACKGROUND
June 2026: Received a Ph.D. in Computer Science and Technology from Beijing University of Posts and Telecommunications (BUPT).
February 2025 – August 2026: Served as a Research Assistant at The Chinese University of Hong Kong, Shenzhen, under the supervision of Professor Haizhou Li and Professor Benyou Wang. Research focused on highly expressive speech synthesis and the development of evaluation frameworks for large-scale speech models.
BIOGRAPHY
Xiang Li holds a Ph.D. in Computer Science and Technology from Beijing University of Posts and Telecommunications and is currently an Associate Research Fellow at the AIM Center, Shenzhen Research Institute of Big Data. Dr. Li’s research interests include speech synthesis, large-scale speech models, speech models for low-resource languages, and industrial intelligent agent systems. Dr. Li has participated in projects under China’s National Key R&D Program, key projects supported by the Joint Funds of the National Natural Science Foundation of China, and multiple industry-sponsored research projects. Dr. Li has substantial research and development experience in training end-to-end large-scale speech models, on-premises deployment, adaptation to domestically developed computing platforms, and domain-specific knowledge base construction, and maintains long-term collaborations with Huawei Noah’s Ark Lab, Yinwang Intelligent Technology Co., Ltd., and other industry partners.
ACADEMIC PUBLICATIONS
• Less is More! On the Composition Pattern of Prompts.[EMNLP 2026]
Xiang Li, Tongqing Shi, Zhirui Li, Jiale Han, Benyou Wang.
• TTS-Hub: Leveraging Modular LoRAs and Arithmetic Composition for Controllable Text-to-Speech.[EMNLP 2026]
Xiang Li, Shiqi Zhang, Zichen Xu, Wenyuan Gu, Hongru Xiao, Bo Cheng, Li Zhou, Jiale Han, Benyou
Wang.
• HiMed: Incentivizing Hindi Reasoning in Medical LLMs. [EMNLP 2026]
Dingfeng Jiang, Han Yan, Chenze Ma, Amit Kumar Jaiswal, Ang Li, Yunxiang Jiang, Xinlei Xiong,
Juhao Liang, Hongru Xiao, Xiang Li†, Fan Bu, Jiale Han, Ruchir Gupta, Prayag Tiwari†, Benyou
Wang†.
• Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction. [CILR 2026]
Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang.
• DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party
Dialogue.[ICME 2026]
Xiang Li, Duyi Pan, Hongru Xiao, Jiale Han, Jing Tang, Jiabao Ma, Wei Wang, Bo Cheng, Jiale Han
• CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models.[NAACL 2024]
Xiang Li, Fan Bu, Ambuj Mehrish, Yingting Li, Jiale Han, Bo Cheng, Soujanya Poria.
• Can Audio Language Models Listen Between the Lines? A Study on Metaphorical Reasoning via the UNSPOKEN.[ACM MM 2025]
Hongru Xiao⋆, Xiang Li⋆, Duyi Pan, Longfei Zhang, ZhixueSong ZhixueSong, Jiale Han, Songning Lai,
Wenshuo Chen, Jing Tang, Benyou Wang.