SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

• URL: http://arxiv.org/abs/2609.02343v1
• Date: Wed, 02 Sep 2026 09:18:27 GMT
• Title: SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval
• Abstract summary: SonicCaps is a large-scale audio captioning dataset comprising 15M captions paired with 700k audio clips.<n>We generate around 24 captions per audio via structured prompt engineering and few- shot generation.<n>Human evaluation shows that SonicCaps is rated significantly higher than existing captioning datasets.
• Score: 23.450464920029308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in audio-language modeling have been driven by large-scale audio captioning datasets. However, existing datasets remain limited by low semantic diversity, generic descriptions lacking acoustic details, and one-to-one audio-caption mappings that poorly reflect the inherent ambiguity of auditory perception. We introduce SonicCaps, 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. To explicitly promote diversity, we generate around 24 captions per audio via structured prompt engineering and few- shot generation, spanning main descriptions, rephrased variants (verbosity, style) and semantic tags. Human evaluation shows that SonicCaps is rated significantly higher than existing captioning datasets, with fine-grained analyses indicating that our captions are perceived as more descriptive and precise, which strongly correlates with quality judgments. Finally, training CLAP models on SonicCaps with a multi-caption sampling strategy consistently improves audio retrieval and zero-shot classification, with stronger generalization across public and commercial benchmarks. We release both SonicCaps and two specialized CLAP models on hugging face: https://huggingface.co/datasets/Zineb/SonicCaps.

Related papers

• AudioMosaic: Contrastive Masked Audio Representation Learning [53.52371029884106]
  We introduce textbfAudioMosaic, a contrastive learning-based audio encoder for general audio understanding.<n>AudioMosaic constructs positive pairs by applying structured time-frequency masking to spectrogram patches.<n>Experiments show that AudioMosaic achieves state-of-the-art performance on several standard audio benchmarks.
  arXiv  Detail & Related papers  (2026-05-14T00:56:51Z)
• AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech [56.08149157180447]
  We introduce AudioCapBench, a benchmark for evaluating audio captioning capabilities of large multimodal models.<n>We evaluate 13 models across two providers (OpenAI, Google Gemini) using both reference-based metrics (METEOR, BLEU, ROUGE-L) and an LLM-as-Judge framework.
  arXiv  Detail & Related papers  (2026-02-27T03:33:37Z)
• ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing [128.8346376825612]
  Key challenges of high-quality image captioning lie in the inherent biases of LVLMs.<n>We propose a scalable debiased captioning strategy, which continuously enriches and calibrates the caption with increased inference budget.<n>Annotating 450K images with ScaleCap and using them for LVLM pretraining leads to consistent performance gains across 11 widely used benchmarks.
  arXiv  Detail & Related papers  (2025-06-24T17:59:55Z)
• TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining [3.5570874721859016]
  We propose a frame-wise contrastive training strategy that learns to align text descriptions with temporal regions in an audio recording.<n>Our model has better temporal text-audio alignment abilities compared to models trained only on global captions when evaluated on the AudioSet Strong benchmark.
  arXiv  Detail & Related papers  (2025-05-12T14:30:39Z)
• Improving Text-To-Audio Models with Synthetic Captions [51.19111942748637]
  We propose an audio captioning pipeline that uses an textitaudio language model to synthesize accurate and diverse captions for audio at scale. We leverage this pipeline to produce a dataset of synthetic captions for AudioSet, named textttAF-AudioSet, and then evaluate the benefit of pre-training text-to-audio models on these synthetic captions.
  arXiv  Detail & Related papers  (2024-06-18T00:02:15Z)
• AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations [1.2101820447447276]
  Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Our method systematically generates audio-caption pairs by augmenting audio clips with natural language labels and corresponding audio signal processing operations. This scalable method produces AudioSetMix, a high-quality training dataset for text-and-audio related models.
  arXiv  Detail & Related papers  (2024-05-17T21:08:58Z)
• WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research [82.42802570171096]
  We introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. Online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. We propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically.
  arXiv  Detail & Related papers  (2023-03-30T14:07:47Z)
• Towards Generating Diverse Audio Captions via Adversarial Training [33.76154801580643]
  We propose a conditional generative adversarial network (C-GAN) to improve diversity of audio captioning systems. A caption generator and two hybrid discriminators compete and are learned jointly, where the caption generator can be any standard encoder-decoder captioning model used to generate captions. The results show that our proposed model can generate captions with better diversity as compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-12-05T05:06:19Z)
• AudioGen: Textually Guided Audio Generation [116.57006301417306]
  We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive model that generates audio samples conditioned on text inputs.
  arXiv  Detail & Related papers  (2022-09-30T10:17:05Z)
• Caption Feature Space Regularization for Audio Captioning [24.40864471466915]
  General audio captioning models achieve the one-to-many training by randomly selecting a correlated caption as the ground truth for each audio. We propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions.
  arXiv  Detail & Related papers  (2022-04-18T17:07:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.