Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning

@misc{polok2026grounding,
  title = {Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning},
  author = {Alexander Polok and Samuele Cornell and Sathvik Udupa and JanHonza'' vCernock'y and Shinji Watanabe and Luk'avs Burget},
  year = {2026},
  eprint = {2606.18134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.18134},
}