Metraipolis › archive › dc_d508648fa5b7
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR — arXiv:2610.08063
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08063
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:23:46.384Z
- SHA-256 of the archived text
ad3d2f8b99d82fc3db5efb84540a8f2fc20ed605ac3ba881de8b4598d7589be2- Stable URL of this page
https://metraipolis.com/documento/dc_d508648fa5b7
How to cite
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR — arXiv:2610.08063 — arXiv (en), https://arxiv.org/abs/2610.08063 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d508648fa5b7 (Metraipolis archive dc_d508648fa5b7, sha256 ad3d2f8b99d82fc3db5efb84540a8f2fc20ed605ac3ba881de8b4598d7589be2)
BibTeX
@misc{dcd508648fa5b7,
title = {HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR — arXiv:2610.08063},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08063},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d508648fa5b7; sha256 ad3d2f8b99d82fc3db5efb84540a8f2fc20ed605ac3ba881de8b4598d7589be2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08063. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We address multilingual speaker-attributed ASR, where systems must determine who spoke when and what was spoken. We investigate two modeling strategies for this problem: a cascaded pipeline that combines speaker diarization with speech-LLM-based ASR, and a unified speech LLM that directly generates speaker labels, timestamps, and transcriptions. Our final submission is based on the cascaded pipeline, consisting of a fine-tuned DiariZen diarization model, a fine-tuned Qwen3-ASR model, and LLM-based generative error correction. For comparison, we also fine-tune VibeVoice-ASR as a unified model using the same official training data. All task-specific fine-tuning and model selection are performed using only the official MLC-SLM data, without external data or pseudo-labels. Experimental results demonstrate that the cascaded system remains more reliable under the MLC-SLM Task 1 conditions, while unified speech LLMs offer a promising direction for future speaker-attributed ASR. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.08063 — 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 2026-10-07T11:15:39.495Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).