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

2026-09-18

AI Summary

研究通过重用语音识别编码器状态与文本嵌入融合的方法，提高长文稿中基于查询的话题定位准确性，尤其在结构化或半结构化语音上效果显著。

Abstract

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 criteria. Cross-dataset experiments further indicate that the benefits are strongest for structured or semi-structured speech, while gains on spontaneous speech are limited and mixed.

Problem

• query-conditioned topic localization
• transcripts
• sentence span
• speech representations

Innovation

• Latent Speech Representations
• Query-Conditioned Topic Localization
• ASR Encoder States
• Sentence-Level Representations