@article{speakerlmendtoendversatilespeakerdiariza,
  title = {SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models},
  author = {Han Yin and Yafeng Chen and Chong Deng and Luyao Cheng and Hui Wang and Chao-Hong Tan and Qian Chen and Wen Wang and Xiangang Li},
  year = {2025},
  eprint = {2508.06372},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.06372},
}