# Beyond Transcripts: A Renewed Perspective on Audio Chaptering

arXiv: https://arxiv.org/abs/2602.08979 · HTML: https://mlsanity.com/paper/2602.08979/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [VidChapters-7M: Video Chapters at Scale](https://mlsanity.com/paper/2309.13952/) (2023)
- [DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering](https://mlsanity.com/paper/2110.05588/) (2021)
- [Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation](https://mlsanity.com/paper/2305.18893/) (2023)
- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning](https://mlsanity.com/paper/2512.19687/) (2025)
- [Outline Generation: Understanding the Inherent Content Structure of Documents](https://mlsanity.com/paper/1905.10039/) (2019)
- [Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs](https://mlsanity.com/paper/2504.00072/) (2025)
- [PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters](https://mlsanity.com/paper/2410.16148/) (2024)
- [Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction](https://mlsanity.com/paper/2305.12450/) (2023)
- [Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation](https://mlsanity.com/paper/2601.02128/) (2026)
- [BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion](https://mlsanity.com/paper/2512.02817/) (2025)
- [Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech](https://mlsanity.com/paper/2512.24517/) (2025)

## Built on by (most cited first, 3 of 3)

- [Do What I Say: A Spoken Prompt Dataset for Instruction-Following](https://mlsanity.com/paper/2603.09881/) (2026)
- [Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026](https://mlsanity.com/paper/2606.04730/) (2026)
- [Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts](https://mlsanity.com/paper/2609.21844/) (2026)

## Abstract (arXiv)

Audio chaptering, the task of segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions unresolved about leveraging audio information, handling ASR errors, and transcript-free evaluation. We address these gaps through three contributions: (1) a systematic comparison between text-based models with acoustic features, a novel audio-only architecture (AudioSeg) operating on learned audio representations, and multimodal LLMs; (2) empirical analysis of factors affecting performance, including transcript quality, acoustic features, duration, and speaker composition; and (3) formalized evaluation protocols contrasting transcript-dependent text-space protocols with transcript-invariant time-space protocols. Our experiments on YTSeg reveal that AudioSeg substantially outperforms text-based approaches, pauses provide the largest acoustic gains, and MLLMs remain limited by context length and weak instruction following, yet MLLMs are promising on shorter audio.