Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features
This work addresses the need for better navigation and processing of spoken content like videos and podcasts, though it is incremental in leveraging acoustic features for an existing task.
The paper tackled the problem of topic segmentation in spoken content by proposing a multi-modal approach that integrates acoustic features, achieving substantial gains over text-only and multi-modal baselines on a large-scale YouTube dataset and showing resilience to ASR noise across multiple languages.
Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user navigation and downstream applications. However, current methods do not fully leverage acoustic features, leaving room for improvement. We propose a multi-modal approach that fine-tunes both a text encoder and a Siamese audio encoder, capturing acoustic cues around sentence boundaries. Experiments on a large-scale dataset of YouTube videos show substantial gains over text-only and multi-modal baselines. Our model also proves more resilient to ASR noise and outperforms a larger text-only baseline on three additional datasets in Portuguese, German, and English, underscoring the value of learned acoustic features for robust topic segmentation.