Analytic Class Incremental Learning for Sound Source Localization with Privacy Protection

Xinyuan Qian, Xianghu Yue, Jiadong Wang, Huiping Zhuang, Haizhou Li
{"title":"Analytic Class Incremental Learning for Sound Source Localization with Privacy Protection","authors":"Xinyuan Qian, Xianghu Yue, Jiadong Wang, Huiping Zhuang, Haizhou Li","doi":"arxiv-2409.07224","DOIUrl":null,"url":null,"abstract":"Sound Source Localization (SSL) enabling technology for applications such as\nsurveillance and robotics. While traditional Signal Processing (SP)-based SSL\nmethods provide analytic solutions under specific signal and noise assumptions,\nrecent Deep Learning (DL)-based methods have significantly outperformed them.\nHowever, their success depends on extensive training data and substantial\ncomputational resources. Moreover, they often rely on large-scale annotated\nspatial data and may struggle when adapting to evolving sound classes. To\nmitigate these challenges, we propose a novel Class Incremental Learning (CIL)\napproach, termed SSL-CIL, which avoids serious accuracy degradation due to\ncatastrophic forgetting by incrementally updating the DL-based SSL model\nthrough a closed-form analytic solution. In particular, data privacy is ensured\nsince the learning process does not revisit any historical data\n(exemplar-free), which is more suitable for smart home scenarios. Empirical\nresults in the public SSLR dataset demonstrate the superior performance of our\nproposal, achieving a localization accuracy of 90.9%, surpassing other\ncompetitive methods.","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Audio and Speech Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07224","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Sound Source Localization (SSL) enabling technology for applications such as surveillance and robotics. While traditional Signal Processing (SP)-based SSL methods provide analytic solutions under specific signal and noise assumptions, recent Deep Learning (DL)-based methods have significantly outperformed them. However, their success depends on extensive training data and substantial computational resources. Moreover, they often rely on large-scale annotated spatial data and may struggle when adapting to evolving sound classes. To mitigate these challenges, we propose a novel Class Incremental Learning (CIL) approach, termed SSL-CIL, which avoids serious accuracy degradation due to catastrophic forgetting by incrementally updating the DL-based SSL model through a closed-form analytic solution. In particular, data privacy is ensured since the learning process does not revisit any historical data (exemplar-free), which is more suitable for smart home scenarios. Empirical results in the public SSLR dataset demonstrate the superior performance of our proposal, achieving a localization accuracy of 90.9%, surpassing other competitive methods.
声源定位的分析类增量学习与隐私保护
声源定位(SSL)技术使监控和机器人等应用成为可能。传统的基于信号处理(SP)的声源定位方法能在特定信号和噪声假设条件下提供分析解决方案,而最新的基于深度学习(DL)的方法则明显优于这些方法。此外,它们通常依赖于大规模注释空间数据,在适应不断变化的声音类别时可能会遇到困难。为了应对这些挑战,我们提出了一种新颖的类增量学习(CIL)方法,称为 SSL-CIL,它通过闭式分析解决方案增量更新基于 DL 的 SSL 模型,避免了因灾难性遗忘而导致的严重准确度下降。特别是,由于学习过程不会重新访问任何历史数据(无范例),因此数据隐私得到了保证,这更适合智能家居场景。公共 SSLR 数据集的实证结果证明了我们的方案性能优越,定位精度达到 90.9%,超过了其他竞争方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信