Transformer-based autoencoder with ID constraint for unsupervised anomalous sound detection

Transformer-based autoencoder with ID constraint for unsupervised anomalous sound detection

Abstract Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However, the AE-based methods could be limited as the feature...

Celý popis

Podrobná bibliografie
Hlavní autoři: Jian Guan, Youde Liu, Qiuqiang Kong, Feiyang Xiao, Qiaoxi Zhu, Jiantong Tian, Wenwu Wang
Médium: Článek
Jazyk:English
Vydáno: SpringerOpen 2023-10-01
Edice:EURASIP Journal on Audio, Speech, and Music Processing
Témata:
Anomalous sound detection
Autoencoder
ID classifier
Weighted anomaly score computation
On-line přístup:https://doi.org/10.1186/s13636-023-00308-4

Internet

https://doi.org/10.1186/s13636-023-00308-4

Podobné jednotky