@misc{arxiv_2609_35613,
  title = {Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities},
  author = {{Xinyuan Qian} and {Yanghao Zhou} and {Ziyang Jiang} and {Yu Chen} and {Xinjia Zhu} and {Xueyan Chen} and {Qiquan Zhang} and {Zexu Pan} and {Jiaying Wang} and {Xianghu Yue} and {Jiadong Wang} and {Björn Schuller} and {Haizhou Li}},
  eprint = {2609.35613},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.35613}
}