Skip to main content

Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning

Publication ,  Conference
Zhang, Y; Suo, H; Wan, Y; Li, M
Published in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
January 1, 2023

This paper proposes an approach for anomalous sound detection that incorporates outlier exposure and inlier modeling within a unified framework by multitask learning. While outlier exposure-based methods can extract features efficiently, it is not robust. Inlier modeling is good at generating robust features, but the features are not very effective. Recently, serial approaches are proposed to combine these two methods, but it still requires a separate training step for normal data modeling. To overcome these limitations, we use multitask learning to train a conformer-based encoder for outlier-aware inlier modeling. Moreover, our approach provides multi-scale scores for detecting anomalies. Experimental results on the MIMII and DCASE 2020 task 2 datasets show that our approach outperforms state-of-the-art single-model systems and achieves comparable results with top-ranked multi-system ensembles.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2023

Volume

2023-August

Start / End Page

5381 / 5385
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, Y., Suo, H., Wan, Y., & Li, M. (2023). Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2023-August, pp. 5381–5385). https://doi.org/10.21437/Interspeech.2023-572
Zhang, Y., H. Suo, Y. Wan, and M. Li. “Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning.” In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023-August:5381–85, 2023. https://doi.org/10.21437/Interspeech.2023-572.
Zhang Y, Suo H, Wan Y, Li M. Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2023. p. 5381–5.
Zhang, Y., et al. “Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning.” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2023-August, 2023, pp. 5381–85. Scopus, doi:10.21437/Interspeech.2023-572.
Zhang Y, Suo H, Wan Y, Li M. Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2023. p. 5381–5385.

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2023

Volume

2023-August

Start / End Page

5381 / 5385