Autoencoder with Group-based Decoder and Multi-task Optimization for Anomalous Sound Detection
Abstract
In industry, machine anomalous sound detection (ASD) is in great demand. However, collecting enough abnormal samples is difficult due to the high cost, which boosts the rapid development of unsupervised ASD algorithms. Autoencoder (AE) based methods have been widely used for unsupervised ASD, but suffer from problems including 'shortcut', poor anti-noise ability and sub-optimal quality of features. To address these challenges, we propose a new AE-based framework termed AEGM. Specifically, we first insert an auxiliary classifier into AE to enhance ASD in a multi-task learning manner. Then, we design a group-based decoder structure, accompanied by an adaptive loss function, to endow the model with domain-specific knowledge. Results on the DCASE 2021 Task 2 development set show that our methods achieve a relative improvement of 13.11% and 15.20% respectively in average AUC over the official AE and MobileNetV2 across test sets of seven machines.
Cite
@article{arxiv.2311.08829,
title = {Autoencoder with Group-based Decoder and Multi-task Optimization for Anomalous Sound Detection},
author = {Yifan Zhou and Dongxing Xu and Haoran Wei and Yanhua Long},
journal= {arXiv preprint arXiv:2311.08829},
year = {2023}
}
Comments
Submitted to the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)