bghorvath/ssl4asd

Code for the paper "Self-Supervised Learning for Anomalous Sound Detection"

Self-Supervised Learning for Anomalous Sound Detection

ASD system utilizing supervised and self-supervised learning for acoustic machine condition monitoring for task 2 "First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring" of the DCASE2023 Challenge.

Instructions

Just start the main.py script for training and evaluation. To run the code, you need to download the development dataset, additional training dataset and the evaluation dataset, and store the files in an './eval_data' and a './dev_data' folder.

Reference

When reusing (parts of) the code, a reference to the following paper would be appreciated:

@unpublished{wilkinghoff2024ssl, author = {Wilkinghoff, Kevin}, title = {Self-Supervised Learning for Anomalous Sound Detection}, note = {Accepted for presentation at International Conference on Acoustics, Speech and Signal Processing (ICASSP), arXiv:2312.09578}, year = {2024} }