Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.08919 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913542002704384 |
|---|---|
| author | Neri, Michael Carli, Marco |
| author_facet | Neri, Michael Carli, Marco |
| contents | In this work, 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. Implementation details, code, and pre-trained models are available in https://github.com/michaelneri/unsupervised-audio-anomaly-detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08919 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Low-complexity Attention-based Unsupervised Anomalous Sound Detection exploiting Separable Convolutions and Angular Loss Neri, Michael Carli, Marco Audio and Speech Processing In this work, 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. Implementation details, code, and pre-trained models are available in https://github.com/michaelneri/unsupervised-audio-anomaly-detection. |
| title | Low-complexity Attention-based Unsupervised Anomalous Sound Detection exploiting Separable Convolutions and Angular Loss |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.08919 |