合成数据用于音视频声源定位究竟能走多远？
How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?
对做音视频多模态定位的研究者，这篇给出了用 text-to-X 生成模型批量合成 VGGSound 克隆数据、并与真实数据混合训练的完整配方，可直接复用于缓解视觉-音频配对数据规模小、语义错位的问题。
原文依据 we leverage synthetic data to create synthetic clones of the VGGSound dataset
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出了首个可扩展的框架，利用来自 text-to-X 模型的合成数据训练声源定位（SSL）模型。尽管 SSL 已取得显著进展，现有模型仍受限于规模有限、未经筛选的真实世界数据集，这些数据集常常存在语义错位问题。此外，新的 SSL 任务与基准的引入，也提升了对更具泛化能力模型的需求。为应对这些挑战，我们利用合成数据构建了 VGGSound 数据集的合成克隆，从而支持完全合成训练与真实-合成混合训练两种方式。我们证明合成数据能够有效地替代、精炼并扩展真实训练数据集。在多个基准上的大量实验表明，合成数据不仅在性能上与真实数据相当，而且在与真实样本结合时还能带来显著提升。我们的发现首次提供了系统性证据，表明合成数据可以作为推进 SSL 模型的一种可扩展且有效的方法。
英文原文摘要 1031 字符
We present the first scalable framework for training sound source localization (SSL) models using synthetic data from text-to-X models. Although SSL has made notable progress, existing models remain constrained by limited-scale, uncurated real-world datasets that often suffer from semantic misalignment. Furthermore, the introduction of new SSL tasks and benchmarks has increased the need for more generalizable models. To address these challenges, we leverage synthetic data to create synthetic clones of the VGGSound dataset, enabling both fully synthetic and hybrid real-synthetic training. We demonstrate that synthetic data can effectively replace, refine, and scale real training datasets. Extensive experiments across multiple benchmarks show that synthetic data not only matches real data in performance but also enables significant improvements when combined with real samples. Our findings provide the first systematic evidence that synthetic data can serve as a scalable and effective approach for advancing SSL models.