freisinger25@interspeech_2025@ISCA

Total: 1

#1 Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation [PDF] [Copy] [Kimi] [REL]

Authors: Steffen Freisinger, Philipp Seeberger, Thomas Ranzenberger, Tobias Bocklet, Korbinian Riedhammer

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.

Subject: INTERSPEECH.2025 - Others