Anomalous Sound Detection using unsupervised and semi-supervised autoencoders and gammatone audio representation
This work addresses early malfunction detection in industrial processes to improve efficiency and savings, but it appears incremental as it builds on existing autoencoder and audio representation methods.
The paper tackled anomalous sound detection in industrial machines by proposing a framework using convolutional autoencoders and Gammatone audio representation, achieving results that substantially exceed baseline performance.
Anomalous sound detection (ASD) is, nowadays, one of the topical subjects in machine listening discipline. Unsupervised detection is attracting a lot of interest due to its immediate applicability in many fields. For example, related to industrial processes, the early detection of malfunctions or damage in machines can mean great savings and an improvement in the efficiency of industrial processes. This problem can be solved with an unsupervised ASD solution since industrial machines will not be damaged simply by having this audio data in the training stage. This paper proposes a novel framework based on convolutional autoencoders (both unsupervised and semi-supervised) and a Gammatone-based representation of the audio. The results obtained by these architectures substantially exceed the results presented as a baseline.