并非所有泛化失败都可挽回：情感音频建模中的四个边界
Not all generalisation failures can be bought back: four boundaries in affective audio modelling
浏览论文内容
中文总结 AI 辅助
本研究针对情感音频建模，揭示模型泛化失败分两类需不同补救措施，通过多语料库等实验明确跨边界损失及预训练模型等无法弥补跨域损失的情况。
中文摘要 AI 辅助
将声学特性映射到情感响应的模型支撑着从音乐推荐到声音设计的各类应用，但这些模型几乎完全是在其训练所用的语料库内进行评估的。当模型在训练语料库之外表现不佳时，标准的应对方式——增加数据量或扩大模型规模——假设所有失败都源于资源不足。本研究表明事实并非如此，且应对方式需采用相反的策略。我们使用四个带标注的声音语料库、四个预训练表示模型以及三个生理记录语料库，将某一映射模型推过应用必须跨越的四个边界：新素材边界、编辑后音频边界、用传感器替代自我报告的边界以及个体听众边界。在每个边界处，我们报告了目标允许的上限、跨越边界后留存的比例，以及缩小差距所需的目标侧观测数据代价。在同一语料库内，预测达到了听众间一致性设定上限的84%；同域语料库交换的代价为该数值的五分之一，而一百个目标标签可弥补三分之二的损失；在音乐与环境声音之间跨越边界的代价为全部损失的五分之四，且四个预训练表示模型均无法弥补该损失；针对生理响应，我们构建的任何信息源均未超过可实现上限的三分之一。因此，“模型无法泛化”是两种诊断结果而非一种，二者需采用互斥的补救措施；将第二种诊断当作第一种处理是代价更高的错误。
英文摘要
Models mapping acoustic properties onto affective response underpin applications from music recommendation to sound design, yet are evaluated almost entirely within the corpus they were fitted on. When one fails outside it, the standard response -- more data, or a larger model -- assumes every failure is a shortage of resources. We show it is not, and that the alternative calls for the opposite remedy. Using four corpora of rated sound, four pretrained representations and three corpora of physiological recording, we pushed one mapping across four boundaries an application must cross: to new material, to edited audio, to a sensor in place of a self-report, and to an individual listener. At each we report the ceiling the target permits, the fraction surviving the crossing, and the price in target-side observations of closing the gap. Within a corpus, prediction reaches 84% of the ceiling set by inter-listener agreement. A same-domain corpus swap costs a fifth of that, and a hundred target labels return two-thirds of the loss. Crossing between music and environmental sound costs four-fifths to all of it, and four pretrained representations recover none of it. Against physiological response no information source we constructed exceeds a third of the attainable ceiling. "The model does not generalise" is therefore two diagnoses, not one, with mutually exclusive remedies; treating the second as the first is the more expensive mistake.
