Aug 2026· 2 citations· ⚡ 1 influential· 46 references
Computer ScienceEngineering
TL;DR
This work introduces LongAudioSpan, a benchmark that spans both duration and depth: it pairs audio from 10 minutes to over 2 hours with 3,240 questions across three cognitive levels, namely perception, understanding, and reasoning.
Abstract
General audio comprehension now covers speech, sound, and music over durations from seconds to hours, driven by large audio-language models (LALMs) that are increasingly omni-modal. Yet the benchmarks that test them still rely on clips of seconds, where scores saturate and models converge; recent long-form efforts extend duration but evaluate long audio much as short clips are. We introduce LongAudioSpan, a benchmark that spans both duration and depth: it pairs audio from 10 minutes to over 2 hours with 3,240 questions across three cognitive levels, namely perception, understanding, and reasoning. Two paths supply the questions, differing in how question content is sourced and how ground truth is obtained. Native QA extracts questions from the audio's content, posing each as a multiple-choice item and an open-ended one graded by detailed rubrics. Anchor QA instead injects ground truth, planting acoustic anchors into the audio and building a perception-to-reasoning chain scored only to the first error. A fully automated pipeline constructs every item through structured captioning, QA generation, and adversarial critic feedback. Evaluating 12 LALMs on LongAudioSpan, we find the hard part comes before reasoning: distilling a few relevant facts from a long, redundant signal. This difficulty grows with audio length and falls hardest on perception, especially temporal grounding. LongAudioSpan is available at https://huggingface.co/datasets/holvan/LongAudioSpan.
MuLA-Bench exposes conditional failure patterns that a single long-context score does not capture, and evaluates ten audio-language models and conducts pooled diagnostics on a fixed eight-model cohort.
Ze-Yu Yang, Xin-Yu Zhang, Zi-Bo Bi et al.· arXiv.org· 2 citations
Large audio language models answer questions about speech, sound, and music, yet their accuracy drops sharply on tasks that need fine-grained acoustic analysis. Judging which of two speakers has the higher pitch demands iterative signal-level reasoning that a content question does not. Current models spend the same com...
Logbook is introduced, a benchmark for hour-scale audio understanding, with recordings ranging from ten minutes to six days, and end-to-end and cascaded systems are compared, finding the task tractable, though the best systems remain below the human reference.
Kwanghee Choi, Suwon Shon, Dmitriy Serdyuk et al.· 0 citations
Temporal grounding is fundamental to audio understanding, yet large audio language models (LALMs) remain weak at it on long audio, where hallucinations compound and annotated data is scarce. Existing benchmarks cover only short clips or offer coarse, synthetic annotations. We introduce EgoSCAPE, a manually verified ben...
Ashutosh Chaubey, Jin-Xi Guo, Minh Tran et al.· 0 citations
SonicCaps is introduced, a large-scale audio captioning dataset comprising ~15M captions paired with ~700k audio clips, generated using a multi-modal large language model (Qwen3-Omni) conditioned on both audio and text and training CLAP models on SonicCaps with a multi-caption sampling strategy consistently improves au...
Zineb Lahrichi, Marc Ferras, G. Richard et al.· 0 citations
Large audio-language models (LALMs) perform strongly on individual audio tasks, but whether these capabilities can be reliably composed remains underexplored. We conduct a controlled diagnostic study of capability composition in LALMs, requiring models to integrate audio-attribute recognition, cue-conditioned segment s...
Chien-Feng Liu, Chih-Kai Yang, Bo-Han Feng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.