Unsupervised acoustic condition monitoring with riemannian geometry

Pavel Lifshits; Ronen Talmon

doi:https://doi.org/10.1109/MLSP49062.2020.9231898

Unsupervised acoustic condition monitoring with riemannian geometry

Pavel Lifshits, Ronen Talmon

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we present an unsupervised method for acoustic condition monitoring. Our method relies on the Riemannian geometry of symmetric and positive-definite (SPD) matrices. Specifically, SPD matrices enable us to build features for multi-channel data, which naturally encode the mutual relationships between the channels. By exploiting the Riemannian geometry of SPD matrices, we show that these features encompass informative comparisons. The proposed anomaly score is then based on a one-class SVM applied to the proposed features and their induced Riemannian distance. We test the proposed method on two benchmarks and show that it achieves state-of-the-art results. In addition, we demonstrate the robustness of the proposed method to noise and to low sampling rates.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020
ISBN (Electronic)	9781728166629
DOIs	https://doi.org/10.1109/MLSP49062.2020.9231898
State	Published - Sep 2020
Event	30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 - Virtual, Espoo, Finland Duration: 21 Sep 2020 → 24 Sep 2020

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2020-September

Conference

Conference	30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020
Country/Territory	Finland
City	Virtual, Espoo
Period	21/09/20 → 24/09/20

Keywords

Acoustic scene classification
Anomaly detection in audio
Condition monitoring
Riemannian geometry
SPD matrices
Unsupervised anomaly detection

All Science Journal Classification (ASJC) codes

Signal Processing
Human-Computer Interaction

Access to Document

https://doi.org/10.1109/MLSP49062.2020.9231898

Cite this

Lifshits, P., & Talmon, R. (2020). Unsupervised acoustic condition monitoring with riemannian geometry. In Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020 Article 9231898 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2020-September). https://doi.org/10.1109/MLSP49062.2020.9231898

@inproceedings{adabfe626c034afbae3252c3dec69815,

title = "Unsupervised acoustic condition monitoring with riemannian geometry",

abstract = "In this paper, we present an unsupervised method for acoustic condition monitoring. Our method relies on the Riemannian geometry of symmetric and positive-definite (SPD) matrices. Specifically, SPD matrices enable us to build features for multi-channel data, which naturally encode the mutual relationships between the channels. By exploiting the Riemannian geometry of SPD matrices, we show that these features encompass informative comparisons. The proposed anomaly score is then based on a one-class SVM applied to the proposed features and their induced Riemannian distance. We test the proposed method on two benchmarks and show that it achieves state-of-the-art results. In addition, we demonstrate the robustness of the proposed method to noise and to low sampling rates.",

keywords = "Acoustic scene classification, Anomaly detection in audio, Condition monitoring, Riemannian geometry, SPD matrices, Unsupervised anomaly detection",

author = "Pavel Lifshits and Ronen Talmon",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 ; Conference date: 21-09-2020 Through 24-09-2020",

year = "2020",

month = sep,

doi = "https://doi.org/10.1109/MLSP49062.2020.9231898",

language = "الإنجليزيّة",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

booktitle = "Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020",

}

Lifshits, P & Talmon, R 2020, Unsupervised acoustic condition monitoring with riemannian geometry. in Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020., 9231898, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2020-September, 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020, Virtual, Espoo, Finland, 21/09/20. https://doi.org/10.1109/MLSP49062.2020.9231898

Unsupervised acoustic condition monitoring with riemannian geometry. / Lifshits, Pavel; Talmon, Ronen.
Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020. 2020. 9231898 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2020-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Unsupervised acoustic condition monitoring with riemannian geometry

AU - Lifshits, Pavel

AU - Talmon, Ronen

PY - 2020/9

Y1 - 2020/9

N2 - In this paper, we present an unsupervised method for acoustic condition monitoring. Our method relies on the Riemannian geometry of symmetric and positive-definite (SPD) matrices. Specifically, SPD matrices enable us to build features for multi-channel data, which naturally encode the mutual relationships between the channels. By exploiting the Riemannian geometry of SPD matrices, we show that these features encompass informative comparisons. The proposed anomaly score is then based on a one-class SVM applied to the proposed features and their induced Riemannian distance. We test the proposed method on two benchmarks and show that it achieves state-of-the-art results. In addition, we demonstrate the robustness of the proposed method to noise and to low sampling rates.

AB - In this paper, we present an unsupervised method for acoustic condition monitoring. Our method relies on the Riemannian geometry of symmetric and positive-definite (SPD) matrices. Specifically, SPD matrices enable us to build features for multi-channel data, which naturally encode the mutual relationships between the channels. By exploiting the Riemannian geometry of SPD matrices, we show that these features encompass informative comparisons. The proposed anomaly score is then based on a one-class SVM applied to the proposed features and their induced Riemannian distance. We test the proposed method on two benchmarks and show that it achieves state-of-the-art results. In addition, we demonstrate the robustness of the proposed method to noise and to low sampling rates.

KW - Acoustic scene classification

KW - Anomaly detection in audio

KW - Condition monitoring

KW - Riemannian geometry

KW - SPD matrices

KW - Unsupervised anomaly detection

UR - http://www.scopus.com/inward/record.url?scp=85096497404&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/MLSP49062.2020.9231898

DO - https://doi.org/10.1109/MLSP49062.2020.9231898

M3 - منشور من مؤتمر

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020

T2 - 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020

Y2 - 21 September 2020 through 24 September 2020

ER -

Unsupervised acoustic condition monitoring with riemannian geometry

Abstract

Publication series

Conference

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this