Metraipolis › archive › dc_ea0a2f38dd5f

DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios — arXiv:2608.22796

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22796
License (as archived)
CC0-1.0
Archived
2026-10-18T10:16:16.055Z
SHA-256 of the archived text
a03d103b2dbf6b0f204684ffe0536c4c395b8b17943cbef0450ef69013898360
Stable URL of this page
https://metraipolis.com/documento/dc_ea0a2f38dd5f

How to cite

DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios — arXiv:2608.22796 — arXiv (en), https://arxiv.org/abs/2608.22796 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea0a2f38dd5f (Metraipolis archive dc_ea0a2f38dd5f, sha256 a03d103b2dbf6b0f204684ffe0536c4c395b8b17943cbef0450ef69013898360)
BibTeX
@misc{dcea0a2f38dd5f,
  title = {DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios — arXiv:2608.22796},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22796},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea0a2f38dd5f; sha256 a03d103b2dbf6b0f204684ffe0536c4c395b8b17943cbef0450ef69013898360},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22796. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-speaker automatic speech recognition (MSASR) aims to jointly predict content transcriptions, speaker identities, and timestamps, thereby addressing the key question of "who spoke what and when" and holds substantial practical value in real-world multi-speaker scenarios. However, MSASR still encounters considerable challenges in the presence of fast turn transitions, overlapping speech, and complex, diverse multi-speaker scenarios. In this work, we propose DiaScriber, an end-to-end multi-speaker diarization and transcription model built on a speech large language model. We first construct diverse data pipelines to cover a wide variety of multi-speaker scenarios and their complexities, including validation and refinement, turn-transition and overlapping-speech simulation, and multimodal annotation. Furthermore, DiaScriber is developed based on the pretrained version of Qwen3.5-Omni through a three-stage training strategy involving continual pretraining, supervised fine-tuning, and reinforcement learning. Experiments show that DiaScriber achieves superior performance over comparison methods across extensive multi-speaker scenario test sets and demonstrates outstanding generalization ability in unseen multi-speaker scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2608.22796 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:09:07.490Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).