Weak Supervised Sound Event Detection Based on Puzzle CAM

作者
Xichang Cai,Yanggang Gan,Menglong Wu,Juan Wu
出处
期刊:IEEE Access [Institute of Electrical and Electronics Engineers]
卷期号:11: 89290-89297 被引量:3
标识
DOI:10.1109/access.2023.3305633
摘要

The sound event detection method based on deep learning has achieved excellent performance. However, the training of high-performance sound event detection models depends on high-quality strong-label datasets, which brings great pressure and cost to the labeling work of datasets. In this paper, we propose a weakly supervised sound event detection method based on Puzzle Class Activation Map(CAM), which aims to obtain the timestamp information of sound events from a sound event classification network trained by weak labels. Specifically, the method discovers more complete regions of sound events by minimizing the difference between the CAM of the original features and the merged CAM of the separated feature blocks. CAM highlights the feature capture in the time dimension during the model decision-making process. We determine the occurrence time of the sound event based on the position of the frame where the feature is located, and use the model classification prediction to guide the CAM output to achieve weakly supervised sound event detection. Experiments on the Domestic Environment Sound Event Detection Dataset demonstrate that our proposed method exhibits superior performance compared to the baseline system in the task of sound event detection. Specifically,The CAM of a single system achieves the best PSDS2 value of 0.732. Furthermore, when utilizing the CAM ensemble of multiple systems, the PSDS2 value improves to 0.751. Both of these values are higher than those achieved by the baseline system.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
谨慎的映雁完成签到,获得积分10
刚刚
12321完成签到,获得积分10
刚刚
浣熊完成签到 ,获得积分10
刚刚
HPP123完成签到 ,获得积分10
刚刚
凶狠的璎完成签到,获得积分10
1秒前
1秒前
Jenny完成签到,获得积分10
1秒前
英俊的铭的应助被rtf采纳,获得10
1秒前
静静的旋律完成签到 ,获得积分10
2秒前
3秒前
白夜完成签到 ,获得积分10
3秒前
3秒前
Tokgo完成签到,获得积分10
4秒前
stone发布了新的文献求助10
4秒前
风吹麦浪的应助被a_mo采纳,获得10
4秒前
cube完成签到,获得积分10
4秒前
威武的海棠花完成签到,获得积分10
4秒前
整齐惋庭完成签到,获得积分10
4秒前
luyue9406的应助被xzn1123采纳,获得10
5秒前
Science完成签到,获得积分10
5秒前
糊涂涂完成签到,获得积分10
6秒前
啦啦啦完成签到,获得积分20
6秒前
jwy完成签到,获得积分10
6秒前
侯侯完成签到,获得积分10
7秒前
欢呼白风完成签到,获得积分10
7秒前
雪糕发布了新的文献求助10
7秒前
奶油布丁完成签到,获得积分10
8秒前
钟D摆完成签到 ,获得积分10
8秒前
赵纤完成签到,获得积分10
8秒前
曾祥完成签到,获得积分10
8秒前
9秒前
从容的丹珍完成签到,获得积分10
9秒前
王宇完成签到,获得积分10
9秒前
lxingu完成签到,获得积分10
9秒前
zhangwenkang完成签到,获得积分10
9秒前
唠叨的访文完成签到,获得积分10
10秒前
10秒前
云烟完成签到,获得积分10
10秒前
Jin完成签到,获得积分10
11秒前
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159288
求助须知:如何正确求助?哪些是违规求助? 9554702
关于积分的说明 21720900
捐赠科研通 7748911
什么是DOI,文献DOI怎么找? 3427184
关于科研通互助平台的介绍 2552111
邀请新用户注册赠送积分活动 2471479