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.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20725
Primary Topic
Music and Audio Processing
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

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

Pengming Feng, Feiyang Xiao, Jian Guan, Qiaoxi Zhu et al.
arXiv (Cornell University)
Music and Audio Processing
preprint

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

Pengming Feng, Feiyang Xiao, Jian Guan, Qiaoxi Zhu, Kejia Zhang, Guangjun He, Li'ang Luo
preprint en

Abstract

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.

arXiv (Cornell University)
Music and Audio Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon