自动分离声音场景的自监督学习

Eduardo Fonseca, A. Jansen, D. Ellis, Scott Wisdom, M. Tagliasacchi, J. Hershey, Manoj Plakal, Shawn Hershey, R. C. Moore, Xavier Serra
{"title":"自动分离声音场景的自监督学习","authors":"Eduardo Fonseca, A. Jansen, D. Ellis, Scott Wisdom, M. Tagliasacchi, J. Hershey, Manoj Plakal, Shawn Hershey, R. C. Moore, Xavier Serra","doi":"10.1109/WASPAA52581.2021.9632739","DOIUrl":null,"url":null,"abstract":"Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and each other is semantically constrained: the sound scene contains the union of source classes and not all classes naturally co-occur. With this motivation, this paper explores the use of unsupervised automatic sound separation to decompose unlabeled sound scenes into multiple semantically-linked views for use in self-supervised contrastive learning. We find that learning to associate input mixtures with their automatically separated outputs yields stronger representations than past approaches that use the mixtures alone. Further, we discover that optimal source separation is not required for successful contrastive learning by demonstrating that a range of separation system convergence states all lead to useful and often complementary example transformations. Our best system incorporates these unsupervised separation models into a single augmentation front-end and jointly optimizes similarity maximization and coincidence prediction objectives across the views. The result is an unsupervised audio representation that rivals state-of-the-art alternatives on the established shallow AudioSet classification benchmark.","PeriodicalId":429900,"journal":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Self-Supervised Learning from Automatically Separated Sound Scenes\",\"authors\":\"Eduardo Fonseca, A. Jansen, D. Ellis, Scott Wisdom, M. Tagliasacchi, J. Hershey, Manoj Plakal, Shawn Hershey, R. C. Moore, Xavier Serra\",\"doi\":\"10.1109/WASPAA52581.2021.9632739\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and each other is semantically constrained: the sound scene contains the union of source classes and not all classes naturally co-occur. With this motivation, this paper explores the use of unsupervised automatic sound separation to decompose unlabeled sound scenes into multiple semantically-linked views for use in self-supervised contrastive learning. We find that learning to associate input mixtures with their automatically separated outputs yields stronger representations than past approaches that use the mixtures alone. Further, we discover that optimal source separation is not required for successful contrastive learning by demonstrating that a range of separation system convergence states all lead to useful and often complementary example transformations. Our best system incorporates these unsupervised separation models into a single augmentation front-end and jointly optimizes similarity maximization and coincidence prediction objectives across the views. The result is an unsupervised audio representation that rivals state-of-the-art alternatives on the established shallow AudioSet classification benchmark.\",\"PeriodicalId\":429900,\"journal\":{\"name\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-05-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WASPAA52581.2021.9632739\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WASPAA52581.2021.9632739","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

摘要

真实世界的声音场景由时变的声源集合组成,每个声源产生的特征声音事件在音频记录中混合在一起。这些组成声音事件与它们的混合以及彼此之间的关联在语义上是受限的:声音场景包含源类的联合,而不是所有类自然地同时出现。基于这一动机,本文探索了使用无监督自动声音分离将未标记的声音场景分解为多个语义链接视图,用于自监督对比学习。我们发现,学习将输入混合与其自动分离的输出相关联,比过去单独使用混合的方法产生更强的表示。此外,我们发现,通过证明一系列分离系统收敛状态都会导致有用且通常互补的示例转换,成功的对比学习并不需要最优源分离。我们最好的系统将这些无监督分离模型集成到单个增强前端中,并共同优化视图之间的相似性最大化和巧合预测目标。结果是一个无监督的音频表示,可以在已建立的浅AudioSet分类基准上与最先进的替代方案相媲美。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Self-Supervised Learning from Automatically Separated Sound Scenes
Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and each other is semantically constrained: the sound scene contains the union of source classes and not all classes naturally co-occur. With this motivation, this paper explores the use of unsupervised automatic sound separation to decompose unlabeled sound scenes into multiple semantically-linked views for use in self-supervised contrastive learning. We find that learning to associate input mixtures with their automatically separated outputs yields stronger representations than past approaches that use the mixtures alone. Further, we discover that optimal source separation is not required for successful contrastive learning by demonstrating that a range of separation system convergence states all lead to useful and often complementary example transformations. Our best system incorporates these unsupervised separation models into a single augmentation front-end and jointly optimizes similarity maximization and coincidence prediction objectives across the views. The result is an unsupervised audio representation that rivals state-of-the-art alternatives on the established shallow AudioSet classification benchmark.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:604180095
Book学术官方微信