发表机构
Shenzhen Coddie Technology Co., Ltd.（深圳科迪科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对婴儿哭声语料库的标签不兼容等问题，通过多级审计探究基础模型的跨数据集迁移能力，提出实用方案并发布工具将不兼容语料库转为联合训练资源。
AI 中文摘要
公开的婴儿哭声语料库规模小、标签不兼容，且几乎总是仅针对单个语料库进行评估。我们探究这种做法隐藏了什么问题以及有什么解决方案。我们通过多级泄露审计（字节级和嵌入级去重，加上语料库内训练-测试近重复审计）筛选了四个哭声语料库，在统一的五类需求本体和共享任务设定下，对四个冻结编码器和一个手工基线进行了探究。该审计揭示了单语料库评估所掩盖的问题：同一编码器的域内宏F1分数波动达0.57-0.80；跨语料库迁移平均为负（负迁移率为0.19-0.35，在30个定向单元中有18个显著，经BH-FDR校正）；349个内容相同的片段组在不同语料库分布中存在矛盾的元数据标签。然而，该审计也揭示了可行的改进方向：在匹配训练规模并移除近重复后，向最嘈杂语料库的迁移效果始终为正，为小型嘈杂语料库提供了实用方案；冻结探针在适度标签预算下达到饱和，而稳定微调在全标签设置下表现更优；域自适应预训练在5-10次少样本设置下显著优于稳定微调（1次少样本优势对优化种子方差不稳健），但在50次少样本及以上设置下无显著优势；在测试的二元共享标签设定中，本体映射联合训练在所有四个编码器-目标组合中均胜出，而直接合并未映射标签会导致F1分数损失高达37分。我们发布了该本体、映射代码和审计流程，将不兼容的哭声语料库转化为可用的联合训练资源。
英文摘要
Public infant cry corpora are small, label-incompatible, and almost always evaluated one corpus at a time. We ask what this practice hides and what fixes it. Across four cry corpora screened by a multi-level leakage audit (byte-level and embedding-level deduplication plus a within-corpus train-test near-duplicate audit), we probe four frozen encoders and a handcrafted baseline under a unified five-class need ontology and shared task formulations. The audit exposes what single-corpus evaluation conceals: within-domain macro-F1 swings by 0.57-0.80 for the same encoder, cross-corpus transfer is negative on average (negative-transfer ratio 0.19-0.35, significant in 18 of 30 directed cells, BH-FDR), and 349 content-identical clip groups carry conflicting metadata labels across corpus distributions. The same audit, however, reveals a consistent way forward. Transfer into the noisiest corpus is consistently positive in effect size at matched training size and after near-duplicate removal, offering a practical recipe for small, noisy corpora. Frozen probes saturate at modest label budgets, while stabilized fine-tuning wins with full labels; domain-adaptive pretraining significantly beats stabilized fine-tuning at 5-10-shot (the 1-shot advantage is not robust to optimization-seed variance) but shows no significant advantage at 50-shot or beyond. In the tested binary, shared-label settings, ontology-mapped joint training wins in all four encoder-by-target combinations, whereas naively merging unmapped labels costs up to 37 F1 points. We release the ontology, mapping code, and audit pipeline, turning incompatible cry corpora into a usable joint-training resource.
Comments18 pages, 7 figures. Under review at AAAI 2027
