SOURCE-LINKED INTELLIGENCE

Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We study query-conditioned topic localization: predicting the sentence span in a transcript that best addresses a topic-title query. To improve span localization, we reuse ASR encoder states as sentence-level representations and fuse them with textual embeddings. This lets lightweight span locators exploit speech information without running a separate audio encoder. Experiments on two public datasets show consistent gains over text-only baselines, especially under strict boundary-matching criter

Read original source ↗ Open in workspace

recordType

paper

region

Global