DCASE 2021 Challenge Task 2 Development Dataset

Description This dataset is the "development dataset" for the DCASE 2021 Challenge Task 2 "Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions". The data consists of the normal/anomalous operating sounds of seven types of real/toy machines. Each recording is a single-channel 10-second audio that includes both a machine's operating sound and environmental noise. The following seven types of real/toy machines are used in this task: Fan Gearbox Pump Slide rail ToyCar ToyTrain Valve Why focus on domain shift? The task setup of the 2020 version was the ASD under ideal conditions. The training- and testing-phase datasets were generated under the same recording conditions, and enough normal training clips recorded under the test domain were made available. In contrast, real-world cases are more complicated and often involve different machine operating conditions between the training and testing phases. A frequent example of this is when the motor speed continuously varies in a conveyor transporting products on a production line based on the production volume in response to product demand. Since there is infinite variation in rotation speed, the sound will also change with infinite variation. Due to the seasonal demand for many products, a limited period of recording training data limits the motor speed during that period (e.g., 200-300 rpm for autumn) and variations in the training data. However, in the test phase, the ASD system must continue to monitor the conveyor through all seasons, so it must be able to monitor all possible motor speed conditions, including those that differ from the training data (such as 100-400 rpm). In addition to the conditions of the machine, environmental noise conditions (SNR, sound characteristics, etc.) also fluctuate uncontrollably depending on the seasonal demand. In such a situation, the normal state's distribution will be changed (i.e., domain shift). Definition First, we define some important terms in this task: "machine type," "section," "source domain," and "target domain." The machine type means the kind of machine, which can be one of seven in this task: fan, gearbox, pump, slide rail, ToyCar, ToyTrain, and valve. The section is defined as a subset of the dataset for calculating performance metrics and is almost identical to what was called "machine ID" in the 2020 version. In the 2020 version, there was a one-to-one correspondence between machine IDs and products, but in the 2021 version, the same product may appear in different sections. Different products may appear in the same section. The source domain means the condition under which most of the training data was recorded, and the target domain means a different condition under which some of the test data was recorded. The source and target domains differ in terms of operating speed, machine load, viscosity, heating temperature, environmental noise, SNR, etc. Data This dataset consists of three sections for each machine type (Section 00, 01, and 02), and each section is a complete set of training and test data. For each section, this dataset provides (i) around 1,000 clips of normal sounds in a source domain for training, (ii) only three clips of normal sounds in a target domain for training, (iii) around 100 clips each of normal and anomalous sounds in the source domain for the test, and (iv) around 100 clips each of normal and anomalous sounds in the target domain for the test. Recording procedure Normal/anomalous operating sounds of machines and related equipment were recorded. Anomalous sounds were collected by deliberately damaging machines. To simplify the task, we only used the first channel of the multi-channel recordings; all recordings were regarded as single-channel recordings from a fixed microphone. We mixed a machine sound with environmental noise, and only noisy recordings are provided as training/test data. The environmental noise clips were recorded in several real factory environments. We will publish papers on the dataset to explain the details of the recording procedure by the submission deadline. Reference labels The given labels for each training/test clip are machine type, section index, normal/anomaly information, and brief attribute information about conditions other than normal/abnormal. The machine type information is given by the directory name. The section index is given by their respective file names. For the datasets other than the evaluation dataset, the normal/anomaly information is given by their respective file names. For the training data, the attribute information is given by their respective file names. Directory structure When you unzip the files downloaded from the GitHub repository and Zenodo, you can see the following directory structure. As described in the Dataset section, the machine type information is given by directory name, and the section index, domain, and the condition information are given by file name, as: /dev_data /fan /train (only normal clips) /section_00_source_train_normal_0000_<attribute>.wav ... /section_00_source_train_normal_0999_<attribute>.wav /section_00_target_train_normal_0000_<attribute>.wav /section_00_target_train_normal_0001_<attribute>.wav /section_00_target_train_normal_0002_<attribute>.wav /section_01_source_train_normal_0000_<attribute>.wav ... /section_02_target_train_normal_0999_<attribute>.wav /source_test /section_00_source_test_normal_0000.wav ... /section_00_source_test_normal_0099.wav /section_00_source_test_anomaly_0000.wav ... /section_00_source_test_anomaly_0099.wav /section_01_source_test_normal_0000.wav ... /section_02_source_test_anomaly_0099.wav /target_test /section_00_target_test_normal_0000.wav ... /section_00_target_test_normal_0099.wav /section_00_target_test_anomaly_0000.wav ... /section_00_target_test_anomaly_0099.wav /section_01_target_test_normal_0000.wav ... /section_02_target_test_anomaly_0099.wav /gearbox (The other machine types have the same directory structure as fan.) /pump /slider /ToyCar /ToyTrain /valve The paths of audio files are: "/dev_data/<machine_type>/train/section_[0-9]+_<domain>_train_normal_[0-9]+_<attribute>.wav" "/dev_data/<machine_type>/source_test/section_[0-9]+_source_test_normal_[0-9]+.wav" "/dev_data/<machine_type>/source_test/section_[0-9]+_source_test_anomaly_[0-9]+.wav" "/dev_data/<machine_type>/target_test/section_[0-9]+_target_test_normal_[0-9]+.wav" "/dev_data/<machine_type>/target_test/section_[0-9]+_target_test_anomaly_[0-9]+.wav" For example, the machine type, section, and domain of "/fan/train/section_01_source_train_normal_0108_strenght_1_big_ambient.wav" are "fan", "section 01", and "source", respectively, and its condition is normal. The machine type, section, and domain of "/gearbox/test/section_00_target_test_anomaly_0024.wav" are "gearbox", "section 00", and "target", respectively, and its condition is anomalous. Baseline system Two simple baseline systems are available on the Github repository [URL] and [URL]. The baseline systems provide a simple entry-level approach that gives a reasonable performance in the dataset of Task 2. They are good starting points, especially for entry-level researchers who want to get familiar with the anomalous-sound-detection task. Conditions of use This dataset was created jointly by Hitachi, Ltd. and NTT Corporation and is available under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. Publication If you use this dataset, please cite all the following three papers: Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi, Noboru Harada, Daisuke Niizumi, Kota Dohi, Ryo Tanabe, Harsh Purohit, and Takashi Endo, "Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions," in arXiv e-prints: 2106.04492, 2021. [URL] Noboru Harada, Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Masahiro Yasuda, Shoichiro Saito, "ToyADMOS2: Another Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection under Domain Shift Conditions," in arXiv e-prints: 2106.02369, 2021. [URL] Ryo Tanabe, Harsh Purohit, Kota Dohi, Takashi Endo, Yuki Nikaido, Toshiki Nakamura, and Yohei Kawaguchi, "MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions," in arXiv e-prints: 2105.02702, 2021. [URL] Feedback If there is any problem, please contact us: Yohei Kawaguchi, [e-mail] Daisuke Niizumi, [e-mail] Keisuke Imoto, [e-mail]

本数据集为DCASE 2021挑战赛任务2「域偏移条件下面向机器状态监测的无监督异常声音检测（Anomalous Sound Detection, ASD）」的开发集（development dataset）。本数据集包含7类真实/玩具机器的正常与异常运行声音，每条录音为单通道10秒音频，同时涵盖机器运行声与环境噪声。本任务使用的7类真实/玩具机器分别为：风扇（Fan）、齿轮箱（Gearbox）、泵（Pump）、滑轨（Slide rail）、ToyCar、ToyTrain、阀门（Valve）。

为何关注域偏移（Domain Shift）？2020版任务的设置为理想条件下的异常声音检测（ASD），其训练与测试阶段的数据集采集条件一致，且可获取测试域下足够的正常训练片段。与之相对，现实场景更为复杂，训练与测试阶段的机器运行工况往往存在差异。一个典型示例为：生产线中输送产品的传送带，其电机转速会根据产品需求与产量持续变化。由于转速存在无限多种变化可能，声音也会随之产生无限变化。由于多数产品存在季节性需求，训练数据的采集周期有限，因此训练阶段的电机转速（例如秋季为200-300 rpm）与数据变化范围受限。但在测试阶段，异常声音检测系统需要全年监测传送带，因此必须能够覆盖所有可能的电机转速工况，包括与训练数据不同的场景（例如100-400 rpm）。除机器工况外，环境噪声条件（信噪比（Signal-to-Noise Ratio, SNR）、声音特性等）也会随季节性需求发生不可控的波动。在此类场景下，正常状态的分布会发生变化，即域偏移（Domain Shift）。

术语定义首先对本任务中的几个重要术语进行定义：机器类型（machine type）、段（section）、源域（source domain）与目标域（target domain）。机器类型指机器的类别，本任务中包含前文提及的7类。段指用于计算性能指标的数据集子集，与2020版中所称的「机器ID（machine ID）」基本一致。2020版中机器ID与产品一一对应，但2021版中同一产品可能出现在不同段中，不同产品也可能出现在同一段中。源域指大部分训练数据的采集工况，目标域指部分测试数据的采集工况。源域与目标域在运行转速、机器负载、粘度、加热温度、环境噪声、信噪比等维度存在差异。

数据集内容本数据集为每类机器类型设置3个段（段00、01和02），每个段包含完整的训练与测试数据。针对每个段，数据集提供：(i) 约1000条源域正常声音片段用于训练；(ii) 仅3条目标域正常声音片段用于训练；(iii) 约100条源域正常声音片段与约100条源域异常声音片段用于测试；(iv) 约100条目标域正常声音片段与约100条目标域异常声音片段用于测试。

录制流程录制了机器及相关设备的正常与异常运行声音。异常声音通过人为损坏机器采集得到。为简化任务，仅使用多通道录音的第一声道，所有录音均视为来自固定麦克风的单通道录音。将机器声音与环境噪声混合，仅提供带噪录音作为训练/测试数据。环境噪声片段采集自多个真实工厂环境。我们将在提交截止日期前发布关于数据集录制细节的论文。

标注信息每个训练/测试片段的标注信息包括机器类型、段索引、正常/异常标签，以及除正常/异常外的工况简要属性信息。机器类型信息由目录名称给出。段索引由各自的文件名给出。除评估集外的数据集，其正常/异常标签由文件名给出。训练数据的属性信息由文件名给出。

目录结构解压从GitHub仓库与Zenodo下载的文件后，将看到如下目录结构。如前文「数据集内容」部分所述，机器类型信息由目录名称给出，段索引、域与工况信息由文件名给出，格式如下：
/dev_data
/fan
/train (仅包含正常片段)
/section_00_source_train_normal_0000_<attribute>.wav
...
/section_00_source_train_normal_0999_<attribute>.wav
/section_00_target_train_normal_0000_<attribute>.wav
/section_00_target_train_normal_0001_<attribute>.wav
/section_00_target_train_normal_0002_<attribute>.wav
/section_01_source_train_normal_0000_<attribute>.wav
...
/section_02_target_train_normal_0999_<attribute>.wav
/source_test
/section_00_source_test_normal_0000.wav
...
/section_00_source_test_normal_0099.wav
/section_00_source_test_anomaly_0000.wav
...
/section_00_source_test_anomaly_0099.wav
/section_01_source_test_normal_0000.wav
...
/section_02_source_test_anomaly_0099.wav
/target_test
/section_00_target_test_normal_0000.wav
...
/section_00_target_test_normal_0099.wav
/section_00_target_test_anomaly_0000.wav
...
/section_00_target_test_anomaly_0099.wav
/section_01_target_test_normal_0000.wav
...
/section_02_target_test_anomaly_0099.wav
/gearbox (其余机器类型的目录结构与fan一致)
/pump
/slider
/ToyCar
/ToyTrain
/valve

音频文件的路径格式如下：
"/dev_data/<machine_type>/train/section_[0-9]+_<domain>_train_normal_[0-9]+_<attribute>.wav"
"/dev_data/<machine_type>/source_test/section_[0-9]+_source_test_normal_[0-9]+.wav"
"/dev_data/<machine_type>/source_test/section_[0-9]+_source_test_anomaly_[0-9]+.wav"
"/dev_data/<machine_type>/target_test/section_[0-9]+_target_test_normal_[0-9]+.wav"
"/dev_data/<machine_type>/target_test/section_[0-9]+_target_test_anomaly_[0-9]+.wav"

举个示例，路径`/fan/train/section_01_source_train_normal_0108_strenght_1_big_ambient.wav`对应的机器类型为fan（风扇）、段为段01、域为源域（source domain），工况为正常。路径`/gearbox/test/section_00_target_test_anomaly_0024.wav`对应的机器类型为gearbox（齿轮箱）、段为段00、域为目标域（target domain），工况为异常。

基线系统GitHub仓库[URL]与[URL]中提供了两个简易基线系统。这些基线系统提供了适用于本任务2数据集的入门级简易方案，可取得合理的性能表现，尤其适合希望熟悉异常声音检测任务的入门研究者。

使用条件本数据集由日立有限公司（Hitachi, Ltd.）与日本电信电话株式会社（NTT Corporation）联合制作，采用知识共享署名-非商业性使用-相同方式共享4.0国际许可协议（Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International, CC BY-NC-SA 4.0）进行发布。

引用要求若使用本数据集，请引用以下三篇论文：
1. Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi, Noboru Harada, Daisuke Niizumi, Kota Dohi, Ryo Tanabe, Harsh Purohit, and Takashi Endo, "Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions", in arXiv e-prints: 2106.04492, 2021. [URL]
2. Noboru Harada, Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Masahiro Yasuda, Shoichiro Saito, "ToyADMOS2: Another Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection under Domain Shift Conditions", in arXiv e-prints: 2106.02369, 2021. [URL]
3. Ryo Tanabe, Harsh Purohit, Kota Dohi, Takashi Endo, Yuki Nikaido, Toshiki Nakamura, and Yohei Kawaguchi, "MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions", in arXiv e-prints: 2105.02702, 2021. [URL]

反馈渠道若有任何问题，请联系：
Yohei Kawaguchi, [e-mail]
Daisuke Niizumi, [e-mail]
Keisuke Imoto, [e-mail]