为音频分类模型提供无需微调的可解释性框架
APEX: Audio Prototype EXplanations for Classification Tasks
- 基于四种声学维度生成可解释原型，分别捕捉瞬时事件、时间模式等
- 在不改变原模型输出的前提下，实现对音频特征的精准定位与解释
- 适合需要理解音频分类决策过程的研究者与工程师
可解释人工智能（XAI）在图像分类中取得显著进展，但音频领域尚缺乏成熟解决方案。现有方法将视觉归因技术直接应用于频谱图，忽略了视听信号的根本差异。尽管原型推理具有潜力，但声学相似性具有多维特性。本文提出 APEX（Audio Prototype EXplanations），一种用于预训练音频分类器的后处理解释框架。APEX 不需对原始主干网络进行微调，严格保持输出不变性。该框架将解释分解为四个视角：基于方块的原型用于定位瞬时事件，基于时间的原型揭示时间模式，基于频率的原型突出频带特征，基于时空联合的原型融合二者信息。由此生成直观、实例驱动的解释，符合声学特性，相比传统梯度方法提供更清晰的语义理解。
原文摘要 · Abstract (English)
Explainable AI (XAI) has achieved remarkable success in image classification, yet the audio domain lacks equally mature solutions. Current methods apply vision-based attribution techniques to spectrograms, overlooking fundamental differences between visual and acoustic signals. While prototype reasoning is promising, acoustic similarity remains multidimensional. We introduce APEX (Audio Prototype EXplanations), a post-hoc framework for interpreting pre-trained audio classifiers. Crucially, APEX requires no fine-tuning of the original backbone and strictly preserves output invariance. APEX disentangles explanations into four perspectives: Square-based prototypes to localize transient events, Time-based for temporal patterns, Frequency-based highlighting spectral bands, and Time-Frequency-based integrating both. This yields intuitive, example-based explanations that respect acoustic properties, providing greater semantic clarity than standard gradient-based methods.
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。