用可听的参考样本解释语音评估模型的判断依据
Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessment
- 基于影响度分析，找出支持或反驳当前判断的训练样例
- 删掉高影响力样本后预测明显变化，验证解释有效性
- 适合临床医生理解模型决策，提升可信赖度
构音障碍严重程度评估对治疗规划和长期监测至关重要，但人工感知评分耗时且存在临床差异。尽管深度学习模型表现优异，其黑箱特性限制了临床应用。现有语音可解释性方法多提供难以理解的声学特征重要性得分。本文提出一种基于影响度的实例级可解释框架，通过支持与竞争训练样本解释每个预测结果。利用基于梯度的影响度近似，计算每句语音的影响分数，识别支持或反驳当前判断的训练样本。通过从5%到20%的受控删除实验验证，移除高影响力样本会系统性改变预测结果。该方法通过关联决策与可感知的参考案例，提供可审计的解释。
原文摘要 · Abstract (English)
Dysarthria severity assessment is essential for therapy planning and longitudinal monitoring, yet manual perceptual rating is time-consuming and variable across clinicians. Although deep learning models achieve strong performance, their black-box nature limits clinical adoption. Existing speech explainability methods typically provide acoustic feature importance scores that are difficult for end-users to interpret. We propose an influence-based, instance-level explainability framework that explains each decision through supportive and competing training samples. Using gradient-based influence approximations, we compute per-utterance influence scores to identify supportive and competing training samples for each prediction. Controlled deletion experiments from 5 to 20 percent validate the explanations, showing that removing highly influential samples systematically shifts predictions. This approach provides auditable explanations by linking decisions to perceptible reference cases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。