Abnormal sound detection based on composite autoencoder Gaussian mixture model

Abstract

Aiming at the problem that the accuracy of abnormal sound detection under unsupervised conditions is not ideal, a novel abnormal sound detection model using composite self-coder combined with Gaussian mixture model is proposed. Firstly, the timing structure and gating mechanism of LSTM are used to improve the feature extraction ability of self-coder (including self-coder and variational self-coder), Secondly, Gaussian Mixture Model (GMM) is used to generate artificial data to improve the robustness of the self-coder against background noise. Experiments are carried out using ToyADMOS and MIMII public data sets, and the results are superior to the naive self-coder and the two improved self-coding models. On the six machines of the experimental data set, AUC increases by 6.34%, 6.65%, 4.03%, 5.57%, 2.38% and 1.07% respectively.