The paper introduces STAG, a post‑hoc framework that provides token‑level spectro‑temporal grounding for captions produced by audio‑based multimodal large language models (MLLMs). STAG estimates temporal support for each token via vocabulary projections of encoded audio, measures frequency‑band relevance through controlled spectral occlusion, and fuses these signals into a spectro‑temporal relevance map. Evaluations across ten explanation methods and four grounding benchmarks show that STAG achieves superior event‑localization performance on every dataset, and counterfactual deletion experiments confirm that removing the identified evidence selectively reduces model confidence and often eliminates the corresponding event from regenerated captions.
arXiv:2606. 01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning.
The paper introduces an evaluation framework for structured audio captions that separates acoustic and semantic aspects, such as timestamped sound event descriptions. It covers five axes—tag sets, descriptions, reasoning, numeric measurements, and spectral profiles—using large language model judges for semantics and deterministic metrics for temporal and acoustic features. Controlled perturbations validate that the metrics are robust to paraphrases but sensitive to real semantic and acoustic errors.
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
arXiv:2609.15215v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal percept...
OmniCapBench is a new deep‑structured evaluation framework for audio‑visual captioning that replaces free‑form text predictions with sets of atomic, verifiable units across entity references, visual shots, and audio events. It uses deterministic constraint checks and localized LLM‑based semantic comparisons to provide reliable, fine‑grained scoring. With 786 densely annotated videos, the benchmark can distinguish perception errors such as temporal grounding failures, identity drift, cross‑modal misalignment, and hallucinations, revealing that current multimodal large language models excel at local perception but struggle with long‑horizon audio‑visual reasoning.
The paper introduces MTG-AD, a 36‑hour dataset of professionally annotated inline audio descriptions for videos, created by blind and sighted professionals. It also presents MTG‑AD‑Eval, a reference‑free evaluation framework that measures how well generated descriptions fit within a video’s natural silences, providing fine‑grained metrics aligned with expert guidelines. Experiments show that while large multimodal language models can reduce speech overlaps, gaps remain in pacing, and users find the model‑generated descriptions highly beneficial for comprehension.
SonicCaps is a large-scale audio captioning dataset featuring approximately 15 million captions paired with 700,000 audio clips, created using the Qwen3-Omni multimodal language model. The dataset emphasizes diversity by generating around 24 captions per clip through structured prompt engineering and few-shot generation, covering main descriptions, rephrased variants, and semantic tags. Human evaluations rate SonicCaps higher than existing datasets, and training CLAP models on it improves audio retrieval and zero-shot classification across public and commercial benchmarks.
Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes.
arXiv:2610.23745v1 Announce Type: cross Abstract: Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and...
Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient c...
arXiv:2606. 07533v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues.
arXiv:2606. 10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision.