UD-ASD：一种用于异常声音检测的统一扩散模型
UD-ASD: A Unified Diffusion Model for Anomalous Sound Detection
浏览论文内容
中文总结 AI 辅助
研究针对异常声音检测，提出含轻量级模块的统一扩散模型，先将音频转对数梅尔频谱图，通过嵌入机器ID引导模型为特定机器重建数据，经高斯混合模型拟合误差分布，实验验证该模型在DCASE2022任务2中相比基线有显著提升。
中文摘要 AI 辅助
异常声音检测旨在通过监测声音来确定是否发生故障。现有方法检测异常范围有限、泛化性差或为每台机器训练单独模型。扩散模型具有强大泛化能力且能在条件引导下生成特定数据。本文提出一个仅带小模块的统一扩散模型。音频先转换为对数梅尔频谱图，轻量级模块将机器ID嵌入条件嵌入中，引导模型为特定机器重建数据，然后扩散模型根据条件重建数据，用高斯混合模型拟合重建误差分布。该统一模型可监测多种机器类型并通过跨域学习学习更基础的特征空间。在DCASE2022挑战任务2上的实验表明，该模型比基线的AUC提高了3.44%，pAUC提高了2.52%，验证了其有效性。
英文摘要
Anomalous Sound Detection (ASD) aims to determine whether faults have occurred by monitoring sounds. Existing methods detect a limited range of anomalies, exhibit poor generalization, or train a separate model for each machine. Diffusion models possess strong generalization and can generate specific data with condition guidance. We propose a unified diffusion model only with a small module. The audio is first transformed into log-Mel spectrograms. The lightweight module embeds machine IDs into condition embeddings, guiding the model to reconstruct data for specific machines. Then diffusion model reconstructs data with condition, using Gaussian Mixture Models to fit the distributions of reconstruction errors. Our unified model could monitor multiple machine types and learn more fundamental feature spaces with cross-domain learning. Experiments on DCASE2022 Challenge Task 2 show that our model achieves 3.44% AUC and 2.52% pAUC improvements over baseline, validating its effectiveness.
发表机构
- University of Science and Technology of China（中国科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。
