Metraipolis › archive › dc_d144eec4a0ce
Speech Language Models for Full-Meeting Speaker Diarization: Capabilities and Limitations — arXiv:2609.23114
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23114
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:00:35.870Z
- SHA-256 of the archived text
2913749224fed6ada39c645e2cbcad003a0eb011feba2d826bf88f9c96c57bd9- Stable URL of this page
https://metraipolis.com/documento/dc_d144eec4a0ce
How to cite
Speech Language Models for Full-Meeting Speaker Diarization: Capabilities and Limitations — arXiv:2609.23114 — arXiv (en), https://arxiv.org/abs/2609.23114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d144eec4a0ce (Metraipolis archive dc_d144eec4a0ce, sha256 2913749224fed6ada39c645e2cbcad003a0eb011feba2d826bf88f9c96c57bd9)
BibTeX
@misc{dcd144eec4a0ce,
title = {Speech Language Models for Full-Meeting Speaker Diarization: Capabilities and Limitations — arXiv:2609.23114},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23114},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d144eec4a0ce; sha256 2913749224fed6ada39c645e2cbcad003a0eb011feba2d826bf88f9c96c57bd9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in Speech Language Models (SpeechLMs), which integrate large language models with speech foundation models, have enabled unified sequence modeling of speech processing tasks. However, many SpeechLM-based approaches to speaker diarization (SD) are tightly coupled with automatic speech recognition (ASR) and evaluated using word-level metrics, making it difficult to assess SD performance independent of ASR accuracy. In this work, we investigate ESPnet-SpeechLM as a token-based backbone for generating SD hypotheses, formulating SD as autoregressive generation of structured tokens conditioned on acoustic input. We systematically compare two output representations: an event-based representation that explicitly models speaker turn onset and offset timestamps, and a frame-based representation that predicts frame-level speaker activity. To provide structured conversational cues, we further incorporate auxiliary tasks including speech activity detection, overlapped speech detection, and speaker turn counting within the output sequence. Across multiple meeting datasets, we find that event-based representations produce more stable and consistent SD outputs than frame-based representations. Our analysis shows that outputs generated by SpeechLMs encode useful temporal SD structure, but full-meeting SD remains limited by recording-level speaker tracking and overlap-related misses. Explicit speaker-linking post-processing substantially reduces speaker confusion, suggesting that robust SpeechLM-based SD requires persistent speaker tracking and overlap-aware generation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.23114 — 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 2026-10-10T00:12:36.395Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).