Query-Conditioned Liquid Temporal Grounding for Long-Form Audio

Yuelan Cheng; Yonggang Zhu; Yongqiang Chen; Peiwei Chang; Yingyi Chen; Wenwu Wang

cs.SDOct 22, 2026

Query-Conditioned Liquid Temporal Grounding for Long-Form Audio

Authors: Yuelan Cheng, Yonggang Zhu, Yongqiang Chen, Peiwei Chang, Yingyi Chen, Wenwu Wang

Organizations: Centre for Vision, Speech and Signal Processing, University of Surrey, UK · School of Artificial Intelligence, Beijing University of Posts and Telecommunications, China · College of Information and Electrical Engineering, China Agricultural University, China

Abstract

Long-form temporal audio grounding (TAG) is challenging because target events often occupy only a small portion of a recording, while queries may impose multiple semantic constraints over a large temporal search space. We propose a query-conditioned liquid temporal grounding framework that injects query semantics through FiLM before a closed-form continuous-time (CfC) network models long-range temporal dependencies. Multiple query-relevant candidates are generated, from which a frozen large audio-language model selects the most compatible one for lightweight local boundary refinement. The pretrained backbone remains frozen, with only lightweight grounding modules optimized. Experiments on the English TAG subset of LAT-Bench show consistent improvements across MOSS-Audio and Qwen3-Omni, while ablations confirm the complementary roles of FiLM and CfC.

Figures & tables

Figure 1: Comparison between short-form and long-form temporal audio grounding.

Figure 2: Overview of the proposed query-conditioned liquid temporal grounding framework.

Reported results [ 6 ]
Model	Setting	mIoU	[email protected]	[email protected]	[email protected]
LAT-Audio	Main Model	50.00	68.10	54.10	34.50
Gemini-2.5-Pro	Main Model	45.30	65.20	53.90	27.70
Gemini-3.0-Pro	Main Model	41.00	51.40	44.80	22.90
Qwen3-Omni	SW	26.20	41.90	25.80	15.50
Qwen3-Omni	QA-SFT	39.20	54.20	41.70	24.50

Table 1: Temporal grounding performance on the English TAG subset of LAT-Bench. SW denotes sliding-window localization, QA-SFT denotes QA-only supervised fine-tuning, and Ref. denotes boundary refinement. Union combines the candidate pools generated with

\rho_{g}{=}0.65

and

\rho_{g}{=}0.80

before LALM-based selection. All metrics are percentages.

Backbone	Pool	Selection	mIoU	[email protected]	[email protected]	[email protected]
MOSS-Audio	Ours	Top-1	38.52	57.98	40.61	19.25
		Oracle	46.72	68.31	50.94	26.76
Qwen3-Omni	$\rho_{g}{=}0.65$	Top-1	42.72	65.02	42.49	19.95
		Oracle	51.04	74.41	55.63	30.52
Qwen3-Omni	$\rho_{g}{=}0.80$	Top-1	41.47	62.44	43.90	18.31
		Oracle	50.66	74.18	54.93	31.22

Table 2: Pre-refinement Top-1 and oracle performance of different candidate pools. Oracle denotes selection of the candidate with the highest IoU to the ground-truth interval from the same pool. All metrics are percentages.

MOSS-Audio
FiLM	Temporal	mIoU	[email protected]	[email protected]	[email protected]
No	None	36.29	54.92	36.38	18.31
Yes	None	33.85	51.88	34.04	17.14
No	CfC	37.21	54.67	37.79	19.71
Yes	GRU	32.00	46.95	32.86	17.84
Yes	CfC	38.52	57.98	40.61	19.25

Table 3: Ablation of query conditioning and temporal modeling. All metrics are percentages. Bold indicates the best result within each backbone.

Temporal Audio Grounding

Temporal audio grounding locates when events, speech, or other audio evidence occur and links those intervals to language.

See all 36 papers

Event-Grounded Question Answering over Long Audio via Structured Retrieval
Feb 16, 2026Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada +2Multimodal RAG Audio QA
Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA
SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
Apr 14, 2026Luoyi Sun, Xiao Zhou, Zeqian Li +3Temporal Audio Grounding Audio-Language Models
Zhejiang University Hangzhou, Zhejiang, China · SAI, Shanghai Jiao Tong University Shanghai, China
GigaChat Audio: Time-aware Large Audio Language Model
Jul 11, 2026Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov +4Audio QA Audio Understanding
SaluteDevices, Russia

Feb 16, 2026J/K move · Enter open · S save

Event-Grounded Question Answering over Long Audio via Structured Retrieval

Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada, Yinyi Guo+1

Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA

Multimodal RAG Audio QA Audio Understanding Audio-Language Models Temporal Audio Grounding Temporal QA

Open paper AskPDF arXiv

Answering natural-language questions over multi-hour audio requires reliable event recognition, temporal grounding, and efficient retrieval. We present LA-RAG (Long Audio Retrieval-Augmented Generation), a structured framework that converts audio into timestamped event records, stores them in an event database, and answers questions using intent-aware retrieval and LLM-based generation. LA-RAG supports two deployment settings: offline grounding mode, in which long recordings are pre-indexed for low-latency querying, and inference-time grounding mode, which performs query-conditioned grounding over shorter, open-ended clips. We evaluate LA-RAG on controlled 24-hour Home-IoT and Industrial-IoT benchmarks and on CASTELLA-QA, derived from real-world audio recordings. The results demonstrate effective long-audio question answering with low query-time latency after grounding and indexing. They also reveal a substantial gap between event detection and temporal localization in current large audio-language models, while showing that explicit timestamped grounding consistently improves temporal reasoning. These findings establish structured grounding and retrieval as a practical complement to generative audio-language models for deployment-oriented long-audio understanding.

Abstract

Temporal Audio Grounding

Explore similar work

Event-Grounded Question Answering over Long Audio via Structured Retrieval

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding

GigaChat Audio: Time-aware Large Audio Language Model