Michael Neri

Michael Neri

Michael Neri (Member, IEEE) received the Ph.D. degree in applied electronics from Roma Tre University in 2025. He is currently a Postdoctoral Research Fellow with the Faculty of Information Technology and Communication Sciences, Tampere University, Finland. His main research interests are in the area of computer vision, deep learning, and audio processing.

Low-complexity Attention-based Unsupervised Anomalous Sound Detection exploiting Separable Convolutions and Angular Loss

Published in IEEE Sensors Letters, 2024

In this letter, a novel deep neural network, designed to enhance the efficiency and effectiveness of unsupervised sound anomaly detection, is presented. The proposed model exploits an attention module and separable convolutions to identify salient time–frequency patterns in audio data to discriminate between normal and anomalous sounds with reduced computational complexity. The approach is validated through extensive experiments using the Task 2 dataset of the DCASE 2020 challenge. Results demonstrate superior performance in terms of anomaly detection accuracy while having fewer parameters than state-of-the-art methods.

Recommended citation: M. Neri and M. Carli, "Low-Complexity Attention-Based Unsupervised Anomalous Sound Detection Exploiting Separable Convolutions and Angular Loss," in IEEE Sensors Letters, vol. 8, no. 11, pp. 1-4, Nov. 2024, Art no. 6014404, doi: 10.1109/LSENS.2024.3480450.
Download Paper