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: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
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:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.
By Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos
arXiv:2607. 06929v1 Announce Type: cross Abstract: Music aesthetic assessment is a challenging yet underexplored problem, requiring models to capture fine-grained, multi-dimensional human perceptual judgments.
By Sirui Zhang, Tianle Wang, Xinyi Tong, Peiyang Yu, Jishang Chen, Liangke Zhao, Haoxin Zhang, Duo Xu, Xin Jin, Feng Yu, Songchun Zhu
The paper investigates whether joint language‑audio embedding models encode human perceptual timbre semantics. It evaluates several state‑of‑the‑art models, finding that LAION‑CLAP aligns best with human‑perceived timbre across instrumental sounds and descriptor‑conditioned audio effects, yet the overall alignment remains limited. The study also notes that reverb‑induced timbre semantics are more consistently captured than equalization‑induced ones.
By Qixin Deng, Bryan Pardo, Thrasyvoulos N Pappas
Chordonomicon is a new dataset of over 666,000 song-level symbolic chord progressions, each annotated with structural parts such as verse, chorus, and bridge, as well as genre and release date. The dataset was compiled by scraping user-generated progressions from multiple sources and shows strong similarity to established prior datasets. The authors also provide a reproducible benchmark suite for next chord prediction, evaluating RNN, GRU, and LSTM models across various context windows and data scales, and find that structural part annotations consistently improve prediction performance.
By Spyridon Kantarelis, Ioannis Liolitsas, Konstantinos Thomas, Vassilis Lyberatos, Edmund Dervakos, Giorgos Stamou
MUUNRiver-Bench is a diagnostic benchmark for music retrieval that uses natural‑language instructions to define relevance for reference‑audio queries. It contains 3,440 tracks across 13 genres and 116 sub‑genres and covers seven tasks such as similar‑music, style‑preserving lyric‑rewriting, cover, and segment retrieval. Experiments with six models in eight configurations show that acoustic encoders favor local identity while text‑aligned encoders favor semantic relations, and that instruction‑aware and audio‑text fusion systems do not consistently outperform their backbones.
By Zhancheng Guo, Congren Dai, Shangda Wu, Jianhuai Hu, Danni Zhao, Xiaobing Li, Maosong Sun
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
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:2606. 30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space.
By Fengjie Lu, Chenang Jiang, Jiarui Hai, Helin Wang, Aaron Yee
arXiv:2607. 10023v1 Announce Type: cross Abstract: Understanding music requires understanding localized relationships across data modalities, e.
By Irmak Bukey, Zachary Novack, Jongmin Jung, Dasaem Jeong, Chris Donahue