跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20725 · v1

Post-fusion Event-aware Time-Frequency Refinement for Audio Moment Retrieval

首次提交 2026-11-16 16:31
版本更新 2026-11-16 16:31
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

Audio Moment Retrieval (AMR) aims to locate the temporal segment within a long audio recording that semantically corresponds to a natural-language query. This task is particularly challenging because query-related audio events are often sparsely distributed and embedded in complex acoustic environments, where background sounds and acoustically similar events can easily obscure the target moments. Existing methods mainly strengthen audio-text semantic interaction to enhance the query-related information in audio frames, but seldom refine the resulting audio representations before temporal localization, limiting their ability to accurately distinguish target events from irrelevant acoustic interference. To address this issue, we propose ETR-AMR, a post-fusion event-aware time-frequency refinement framework for AMR. Specifically, an event-aware time-frequency refinement (ETR) strategy is proposed after audio-text interaction to refine fused audio frame features before temporal moment localization. ETR consists of two complementary mechanisms: time frame gating and frequency refinement. The time frame gating mechanism estimates frame-wise event relevance to emphasize query-related audio frames and suppress redundant temporal responses, while frequency refinement applies learnable time-frequency reweighting to enhance discriminative event-related frequency patterns and reduce background-dominant interference. By jointly refining fused audio frame features in the temporal and frequency domains, ETR produces more discriminative event-aware features for accurate temporal boundary prediction. Experiments on four AMR datasets demonstrate that ETR-AMR achieves superior performance compared with existing methods, especially on the high-quality CASTELLA benchmark. Duration-wise analysis further confirms the effectiveness of ETR for medium and long audio moments.

作者备注:Accepted by NCMMSC 2026.Demo Page: https://littleflyingsheep.github.io/etr-amr-demo/

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 16:31 · 最新观测版本

Post-fusion Event-aware Time-Frequency Refinement for Audio Moment Retrieval

Audio Moment Retrieval (AMR) aims to locate the temporal segment within a long audio recording that semantically corresponds to a natural-language query. This task is particularly challenging because query-related audio events are often sparsely distributed and embedded in complex acoustic environments, where background sounds and acoustically similar events can easily obscure the target moments. Existing methods mainly strengthen audio-text semantic interaction to enhance the query-related information in audio frames, but seldom refine the resulting audio representations before temporal localization, limiting their ability to accurately distinguish target events from irrelevant acoustic interference. To address this issue, we propose ETR-AMR, a post-fusion event-aware time-frequency refinement framework for AMR. Specifically, an event-aware time-frequency refinement (ETR) strategy is proposed after audio-text interaction to refine fused audio frame features before temporal moment localization. ETR consists of two complementary mechanisms: time frame gating and frequency refinement. The time frame gating mechanism estimates frame-wise event relevance to emphasize query-related audio frames and suppress redundant temporal responses, while frequency refinement applies learnable time-frequency reweighting to enhance discriminative event-related frequency patterns and reduce background-dominant interference. By jointly refining fused audio frame features in the temporal and frequency domains, ETR produces more discriminative event-aware features for accurate temporal boundary prediction. Experiments on four AMR datasets demonstrate that ETR-AMR achieves superior performance compared with existing methods, especially on the high-quality CASTELLA benchmark. Duration-wise analysis further confirms the effectiveness of ETR for medium and long audio moments.

查看此版本解读 →查看此版本原文 ↗