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.
By Zineb Lahrichi, Marc Ferras, Ga\"el Richard, Geoffroy Peeters
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.
By Weijie Wu, Junbo Li, Lin Li, Jun Fang, Qingyang Hong
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.
By Lucia Cascone, Valeria Fraenza, Michele Nappi, Fabio Narducci, Benedetto Simone
arXiv:2608. 04479v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has recently achieved remarkable progress in synthesizing realistic audio from natural language descriptions.
By Jinting Wang, Yuguang Yang, Shengyu Li, Yan Rong, Shan Yang, Xiaoda Yang, Li Liu
arXiv:2606. 07387v1 Announce Type: new Abstract: State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages.
By Yun-Chen Cheng, Tzu-Hung Huang, Chih-Pin Tan
arXiv:2511. 16757v2 Announce Type: replace-cross Abstract: Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored.
By Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo, Yiwen Shao, Hao Zhang, Dong Yu
arXiv:2509. 14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios.
By Kartik Hegde, Rehana Mahfuz, Yinyi Guo, Erik Visser
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.
By Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu, Jingqi Chen, Ke Chen, Wenxuan Wang, Yang Wang, Yaozhou Jiang, Yi Jiang, Zhengyuan Lin, Ziqi Chen, Zhaoye Fei, Chenghao Liu, Jun Zhan, Kang Yu, Kexin Huang, Mingshu Chen, Qinyuan Cheng, Ruixiao Li, Shimin Li, Songlin Wang, Yang Gao, Yiyang Zhang, Xipeng Qiu
VidOmni-Bench is a new benchmark for fine‑grained video understanding that asks models to verify whether each event in dense video captions is supported by the video. It contains 500 videos covering five complexity types and durations from 4 seconds to 90 minutes, and uses human‑verified sentence‑level labels to create hard negatives. Experiments show that Video‑LLMs often hallucinate events, struggle to detect incorrect descriptions, and exhibit varying weaknesses depending on video complexity and duration.
By Changbeen Kim, Junwon Chang, Kipyo Kim, Risa Shinoda, Kuniaki Saito, Donghyun Kim
arXiv:2608. 09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive.
By Oluwanifemi Bamgbose, Simon Rosen, Jash Shah, Lindsay Devon Brin, Hoang H Nguyen, Anke Koelzer, Rachel Hansen, Tara Bogavelli, Fanny Riols
arXiv:2511. 05550v3 Announce Type: replace-cross Abstract: Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio.
By Daniel Chenyu Lin, Michael Freeman, John Thickstun
The paper evaluates whether music‑text models truly capture fine‑grained musical meaning by introducing attribute‑swap perturbations that exchange properties such as timbre or order between instruments in a caption. Four contrastive models and one large audio‑language model were tested to see if they would score higher on the original caption than on the perturbed one. The results show that none of the contrastive models reliably distinguish the captions, and the audio‑language model’s advantage stems mainly from language priors, indicating that CLAP scores behave like a bag‑of‑words and fail to reflect attribute bindings.
By Yuan-Chiao Cheng, Alexander Lerch