Research on Acoustic Anomaly Detection in Public Scene Based on Multi-dimensional Feature Space

Tongan Ji*, Wenzhong Lou, Fei Zhao, Zilong Su

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Aiming at the problem of detection and recognition of abnormal sound events in public scenes, this paper proposes an algorithm based on machine hearing algorithm to automatically complete the detection and classification of abnormal sound activities. Through real-time monitoring of the scene, template matching is carried out with the list of abnormal events to realize the judgment of abnormal sound activities in public scenes. The feature mapping of multi-dimensional vector space is completed for the speech segments of potential acoustic activity. The feature vector includes not only the own features, but also the features related to the event list template. The SVM algorithm based on Gaussian radial basis function is used to train and test the performance on the self-organized dataset. The results show that the algorithm has a good performance in detecting the accuracy of classification.

源语言英语
主期刊名Proceedings of 2021 International Conference on Autonomous Unmanned Systems, ICAUS 2021
编辑Meiping Wu, Yifeng Niu, Mancang Gu, Jin Cheng
出版商Springer Science and Business Media Deutschland GmbH
1214-1224
页数11
ISBN(印刷版)9789811694912
DOI
出版状态已出版 - 2022
活动International Conference on Autonomous Unmanned Systems, ICAUS 2021 - Changsha, 中国
期限: 24 9月 202126 9月 2021

出版系列

姓名Lecture Notes in Electrical Engineering
861 LNEE
ISSN(印刷版)1876-1100
ISSN(电子版)1876-1119

会议

会议International Conference on Autonomous Unmanned Systems, ICAUS 2021
国家/地区中国
Changsha
时期24/09/2126/09/21

指纹

探究 'Research on Acoustic Anomaly Detection in Public Scene Based on Multi-dimensional Feature Space' 的科研主题。它们共同构成独一无二的指纹。

引用此