{"ID":2822584,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.02128","arxiv_id":"2601.02128","title":"Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation","abstract":"Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hierarchical topic segmentation in transcripts, generating multi-level tables of contents that capture both topic and subtopic boundaries. We compare zero-shot prompting and LoRA fine-tuning on large language models, while also exploring the integration of high-level speech pause features. Evaluations on English meeting recordings and multilingual lecture transcripts (Portuguese, German) show significant improvements over established topic segmentation baselines. Additionally, we adapt a common evaluation measure for multi-level segmentation, taking into account all hierarchical levels within one metric.","short_abstract":"Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hierarchical topic segmentation in transcripts, generating multi-level tables of contents that capture both topic and subtopic boundaries. We...","url_abs":"https://arxiv.org/abs/2601.02128","url_pdf":"https://arxiv.org/pdf/2601.02128v1","authors":"[\"Steffen Freisinger\",\"Philipp Seeberger\",\"Thomas Ranzenberger\",\"Tobias Bocklet\",\"Korbinian Riedhammer\"]","published":"2026-01-05T14:00:48Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"eess.AS\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}