用状态空间模型提升呼吸音分类，更敏感捕捉异常局部特征。
Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification
- 改用状态空间模型替代自注意力，更好保留高频声学细节。
- 提出频谱感知正则化与双轴混叠对比学习，提升模型性能。
- 在ICBHI数据集上达64.48%，比传统方法高5个百分点，适合医疗音频分析。
当前呼吸音分类（RSC）多采用基于CLS-token的自注意力架构（如AST），虽能建模全局上下文，但存在低通滤波效应，削弱对局部异常模式的敏感性。本文研究状态空间模型（SSMs）作为RSC的替代主干网络。基于蒸馏音频状态空间模型（Distilled Audio State Space），通过频谱响应曲线分析中间表示，发现其对中高频空间频率成分有更强保留能力。据此，我们在特定层引入高斯卷积实现频谱感知正则化。进一步设计针对SSM音频模型的双轴混叠对比学习策略，增强鲁棒表征学习。在ICBHI基准测试中，本方法取得64.48%的准确率，优于AST基线5个百分点。代码已开源：https://github.com/RSC-Toolkit/Lung-SRAD。
原文摘要 · Abstract (English)
Recent respiratory sound classification (RSC) studies largely rely on CLS-token driven self-attention architectures such as the Audio Spectrogram Transformer (AST). While effective at modeling global context, recent analyses suggest a low-pass filtering behavior that may reduce sensitivity to localized abnormal patterns. In this work, we investigate State Space Models (SSMs) as an alternative backbone for RSC. Using the Distilled Audio State Space model, we analyze intermediate representations through spectral response curves and observe stronger preservation of mid-to-high spatial-frequency components. Based on these observations, we introduce spectral-aware layer regularization using Gaussian convolution applied to selected layers. We further propose Dual-Axis Patch-Mix contrastive learning tailored to SSM-based audio models for robust representation learning. Experiments on the ICBHI benchmark show that our approach achieves 64.48% score, outperforming the AST baseline by 5%. Code is available at https://github.com/RSC-Toolkit/Lung-SRAD.
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。