Dcase2020
DCASE2020 Task2 dataset:
Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions.
Description¶
The main challenge of this task is to detect unknown anomalous sounds under the condition that only normal sound samples have been provided as training data. In real-world factories, actual anomalous sounds rarely occur and are highly diverse. Therefore, exhaustive patterns of anomalous sounds are impossible to deliberately make and/or collect. This means we have to detect unknown anomalous sounds that were not observed in the given training data. This point is one of the major differences in premise between ASD for industrial equipment and the past supervised DCASE tasks for detecting defined anomalous sounds such as gunshots or a baby crying.
Homepage¶
https://dcase.community/challenge2020/task-unsupervised-detection-of-anomalous-sounds
Original Dataset¶
- Type of experiments: labelled data
- Format: wav file, int16
- Size: ~ 16.5 Gb, unzipped
- Sampling rate: 16000 Hz
- Recording duration: 10 seconds
- Number of channels: 1
- Label: 'normal', 'anomaly' or 'unknown'
- Split: train, test, query
Built Dataset¶
Split: ['train', 'test', 'query']
Features¶
- 'signal': {'channel': audio},
- 'sampling_rate': 16000,
- 'metadata': { 'Machine': type of machine, 'ID': machine ID, 'FileName': original file name, }
Notes¶
The training data contains only normal samples while the test data contains both normal and anomal samples.
Dcase2020
¶
Bases: tfds.core.GeneratorBasedBuilder