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.
arXiv:2511. 16757v2 Announce Type: replace-cross Abstract: Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored.
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.
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.
AVSD-Scenes is a new dataset of 12,291 audio‑visual scene descriptions for urban environments, built from the TAU Urban Audio‑Visual Scenes dataset. The descriptions are generated by first creating modality‑specific text with Qwen2‑Audio‑7B and Qwen2.5‑VL‑7B, then merging them with large language models (Qwen3‑14B, Mistral‑Small‑3.2‑24B‑Instruct‑2506, Gemma‑3‑27B‑it) to produce multimodal narratives that combine auditory and visual cues. Benchmarks show that these multimodal descriptions improve semantic alignment, cross‑modal retrieval, and scene classification accuracy (up to 95.4%) while remaining discriminative even without explicit scene labels.
The paper introduces StyleInstructCaps, a benchmark for controllable speaking‑style captioning (SSC) in audio‑language models. SSC generates natural language descriptions of speech delivery, capturing paralinguistic attributes such as vocal timbre, prosody, and expressivity, and requires dimension‑specific style captions rather than a single undifferentiated description. The benchmark provides a dataset and evaluation framework that assesses metadata groundedness, hallucination, instruction‑following ability, generalization to unseen instructions and audio datasets, and speaker‑style consistency, and shows that instruction‑diverse training improves groundedness, controllability, and speaker consistency across nine state‑of‑the‑art models.
arXiv:2607. 27109v2 Announce Type: cross Abstract: With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions.
arXiv:2606. 06615v1 Announce Type: cross Abstract: Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.
arXiv:2607. 10299v1 Announce Type: new Abstract: Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues.
arXiv:2604.18360v4 Announce Type: replace-cross Abstract: Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; how...
arXiv:2606. 14591v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio 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.
arXiv:2502. 16584v2 Announce Type: replace-cross Abstract: Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs).