SOURCE-LINKED INTELLIGENCE

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal perception, particularly in precise event localization. Existing approaches primarily post-train LALMs to predict event boundaries as timestamp tokens. However, this generative formulation lacks explicit correspondence between the timestamp predictions and fine-grained acoustic evidence, limiting the precision and reliability of temporal localization. To address this issue, we augment the LALM with a dedicated frame-level grounding model while leveraging

Read original source ↗ Open in workspace

recordType

paper

region

Global