Can Large Audio Language Models Understand Audio Well? Speech, Scene and Events Understanding Benchmark for LALMs
Year: 2026
Type: conference-paper
Abstract: Recently, Large Audio Language Models (LALMs) have progressed rapidly, demonstrating their strong efficacy in universal audio understanding through cross-modal integration. To evaluate LALMs' audio understanding performance, researchers have proposed different benchmarks. However, key aspects for real-world interactions are underexplored in existing benchmarks, i.e., audio signals typically contain both speech and non-speech components, and energy levels of these components can vary significantly across different scenarios. Moreover, most benchmarks do not consider the joint understanding of speech, scene, and events within the same audio clip. In this work, we introduce SSEU-Bench, the first versatile audio understanding benchmark that explicitly accounts for energy differences between speech and non-speech audio, with both independent and joint understanding settings for speech, scene, and events. Furthermore, we demonstrate that some LALMs tend to underperform on certain tasks in a joint understanding setting. To address this issue, we introduce Chain-of-Thought, which effectively improves LALMs' joint audio understanding performance by decomposing complex tasks into simpler reasoning steps.
Authors: Han Yin, Jung-Woo Choi
Institution: Korea Advanced Institute of Science and Technology
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417080425
FWCI:
Cites:
Cited by:
Related to: