鲁棒生成音频质量评估：分离质量与虚假相关性
Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations
AI总结：
针对AI生成内容快速增多带来的质量评估需求，本文通过域对抗训练分离真实质量与虚假相关性，提出针对不同MOS方面的领域定义策略，有效缓解声学偏见，提升与人类评分的关联性及泛化能力。
摘要：
随着AI生成内容的迅速发展，亟需稳健的感知质量评估指标。然而，自动Mean Opinion Score（MOS）预测模型常受数据稀缺影响，易学习特定数据集的声学特征而非通用质量特征。为此，本文利用域对抗训练（DAT）分离真实质量感知与干扰因素。不同于以往依赖静态领域先验的方法，我们系统研究了从显式元数据驱动标签到隐式数据驱动聚类的领域定义策略。研究发现，不存在
英文摘要：
The rapid proliferation of AI-Generated Content (AIGC) has necessitated robust metrics for perceptual quality assessment. However, automatic Mean Opinion Score (MOS) prediction models are often compromised by data scarcity, predisposing them to learn spurious correlations-- such as dataset-specific acoustic signatures-- rather than generalized quality features. To address this, we leverage domain adversarial training (DAT) to disentangle true quality perception from these nuisance factors. Unlike prior works that rely on static domain priors, we systematically investigate domain definition strategies ranging from explicit metadata-driven labels to implicit data-driven clusters. Our findings reveal that there is no "one-size-fits-all" domain definition; instead, the optimal strategy is highly dependent on the specific MOS aspect being evaluated. Experimental results demonstrate that our aspect-specific domain strategy effectively mitigates acoustic biases, significantly improving correlation with human ratings and achieving superior generalization on unseen generative scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
