解锁强监督：通用音频预训练方法的数据中心研究
Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods
该论文的数据中心视角（高质量标注数据优先于预训练目标选择）对视觉预训练有直接借鉴意义：可复用其高保真标注生成流程与统一标签系统构建方法，并启示视觉领域在扩大预训练数据时优先提升数据质量与覆盖度。
原文依据 Our experiments suggest that data quality and coverage are the primary drivers of performance, while the choice of objective dictates downstream task specialization.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前音频预训练旨在学习面向广泛音频理解任务的统一表征，但仍呈碎片化，且从根本上受限于对弱、噪声大且规模有限的标签的依赖。借鉴视觉基础预训练的蓝图，我们认为音频领域必须首先建立自身的大规模强监督框架。我们引入一种新的数据中心流程，利用高保真描述生成器创建SOTA质量的描述，并构建首个桥接语音、音乐和环境声音的统一标签系统（UTS）。随后，我们在这些强源数据上对不同预训练目标进行系统性比较研究。实验表明，数据质量和覆盖度是性能的主要驱动因素，而目标的选择决定下游任务的特化方向。
英文原文摘要 875 字符
Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons from vision's foundational pre-training blueprint, we argue that the audio field must first establish its own large-scale, strong supervision framework. We introduce a new data-centric pipeline that leverages a high-fidelity captioner to create SOTA-quality captions and the first Unified Tag System (UTS) that bridges speech, music, and environmental sounds. We then conduct a systematic comparative study of different pre-training objectives on these strong source data. Our experiments suggest that data quality and coverage are the primary drivers of performance, while the choice of objective dictates downstream task specialization.