Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding

TL;DR

This paper introduces LAT-Audio, a new framework and dataset for improving long-form audio understanding by emphasizing temporal awareness through progressive reasoning and iterative local context integration.

Contribution

The paper presents LAT-Audio, a novel approach with a new dataset and benchmark tailored for long-form audio temporal tasks, addressing previous limitations in temporal alignment accuracy.

Findings

LAT-Audio outperforms existing models on long-form temporal tasks.

The new dataset LAT-Chronicle contains 1.2k hours of annotated long-form audio.

The benchmark supports three core long-form audio understanding tasks.

Abstract

While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as audio duration grows. We attribute these limitations to the lack of data, benchmarks, and modeling approaches tailored for long-form temporal awareness. To bridge this gap, we first construct LAT-Chronicle, a 1.2k hour long-form audio dataset with temporal annotations across real-world scenarios. We further develop LAT-Bench, the first human-verified benchmark supporting audio up to 30 minutes while covering three core tasks: Dense Audio Caption, Temporal Audio Grounding, and Targeted Audio Caption. Leveraging these resources, we propose LAT-Audio, formulating temporal awareness as a progressive global-to-local reasoning paradigm. A global timeline is first constructed as an aligned temporal-semantic context,and the Think-With-Audio Chain-of-Thought (TWA-CoT) is then introduced to perform iterative reasoning by incorporating local audio information via tool use. Experiments show that LAT-Audio surpasses existing models on long-form audio temporal awareness tasks and improves robustness to input duration. We release the dataset, benchmark, and model to facilitate future research at https://github.com/alanshaoTT/LAT-Audio-Repo.