Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-09-18 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21

Category: cs.CL · 自然语言处理 · first seen 2026-09-21

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

Read on arXiv →

#7 most recent of 200 cs.CL papers we have recorded · ↑ newer: TrialAtlas: Multi-Agent Research Organization for Clinical Trial Desig · ↓ older: RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree
Cite this page: Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts: the #7 most recent of 200 cs.CL papers we have recorded (as of 2026-09-18). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/reusing-latent-speech-representations-for-query-conditioned-topic-localization-i.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions