Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks
This work addresses the problem of detecting abnormal acoustic signals for applications like audio monitoring, but it is incremental as it builds on existing GAN and semi-supervised methods.
The paper tackles acoustic anomaly detection by proposing a Gaussian Mixture Generative Adversarial Network (GMGAN) under a semi-supervised learning framework to address class imbalance and lack of abnormal instances, achieving state-of-the-art results on the DCASE dataset.
Acoustic anomaly detection aims at distinguishing abnormal acoustic signals from the normal ones. It suffers from the class imbalance issue and the lacking in the abnormal instances. In addition, collecting all kinds of abnormal or unknown samples for training purpose is impractical and timeconsuming. In this paper, a novel Gaussian Mixture Generative Adversarial Network (GMGAN) is proposed under semi-supervised learning framework, in which the underlying structure of training data is not only captured in spectrogram reconstruction space, but also can be further restricted in the space of latent representation in a discriminant manner. Experiments show that our model has clear superiority over previous methods, and achieves the state-of-the-art results on DCASE dataset.