@article{integratingaudiovisualandsemantic,
  title = {Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization},
  author = {Luyao Cheng and Hui Wang and Siqi Zheng and Yafeng Chen and Rongjie Huang and Qinglin Zhang and Qian Chen and Xihao Li},
  year = {2024},
  eprint = {2408.12102},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.12102v1},
}