We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: ``First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring''. The main goal is to enable rapid deployment of ASD systems for new kinds of machines without the need for hyperparameter tuning. In the past ASD tasks, developed methods tuned hyperparameters for each machine type, as the development and evaluation datasets had the same machine types. However, collecting normal and anomalous data as the development dataset can be infeasible in practice. In 2023 Task 2, we focus on solving the first-shot problem, which is the challenge of training a model on a completely novel machine type. Specifically, (i) each machine type has only one section (a subset of machine type) and (ii) machine types in the development and evaluation datasets are completely different. Analysis of 86 submissions from 23 teams revealed that the keys to outperform baselines were: 1) sampling techniques for dealing with class imbalances across different domains and attributes, 2) generation of synthetic samples for robust detection, and 3) use of multiple large pre-trained models to extract meaningful embeddings for the anomaly detector.

翻译：我们呈现了检测与分类声学场景和事件（DCASE）2023挑战赛任务2的描述："面向机器状态监测的首次无监督异常声音检测（ASD）"。其主要目标是实现针对新型机器的ASD系统快速部署，无需进行超参数调优。在以往的ASD任务中，由于开发数据集与评估数据集使用相同的机器类型，所开发的方法需为每种机器类型调优超参数。然而，在实际应用中，收集正常与异常数据作为开发数据集并不可行。2023年任务2聚焦于解决"首次问题"，即针对完全新颖的机器类型训练模型的挑战。具体而言：（i）每种机器类型仅包含一个截面（机器类型的子集），（ii）开发数据集与评估数据集中的机器类型完全不同。对来自23个团队的86份提交分析表明，超越基线方法的关键在于：1）针对不同领域和属性间类别不平衡的采样技术，2）生成合成样本以实现鲁棒检测，3）利用多个大型预训练模型提取有效嵌入用于异常检测器。