• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

DISCO：一种用于声学信号不确定性感知分割的深度学习集成方法。

DISCO: A deep learning ensemble for uncertainty-aware segmentation of acoustic signals.

作者信息

Colligan Thomas, Irish Kayla, Emlen Douglas J, Wheeler Travis J

机构信息

Department of Pharmacy Practice & Science, University of Arizona, Tucson, AZ, USA.

Department of Computer Science, University of Montana, Missoula, MT, USA.

出版信息

bioRxiv. 2023 Jan 26:2023.01.24.525459. doi: 10.1101/2023.01.24.525459.

DOI:10.1101/2023.01.24.525459
PMID:36747788
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9900853/
Abstract

Recordings of animal sounds enable a wide range of observational inquiries into animal communication, behavior, and diversity. Automated labeling of sound events in such recordings can improve both throughput and reproducibility of analysis. Here, we describe our software package for labeling sound elements in recordings of animal sounds and demonstrate its utility on recordings of beetle courtships and whale songs. The software, DISCO, computes sensible confidence estimates and produces labels with high precision and accuracy. In addition to the core labeling software, it provides a simple tool for labeling training data, and a visual system for analysis of resulting labels. DISCO is open-source and easy to install, it works with standard file formats, and it presents a low barrier of entry to use.

摘要

动物声音的录音能够对动物交流、行为和多样性进行广泛的观察性探究。在此类录音中对声音事件进行自动标注可以提高分析的通量和可重复性。在这里，我们描述了用于标注动物声音录音中声音元素的软件包，并展示了其在甲虫求偶和鲸鱼歌声录音上的效用。该软件DISCO能够计算合理的置信度估计，并生成高精度和高准确度的标签。除核心标注软件外，它还提供了一个用于标注训练数据的简单工具，以及一个用于分析所得标签的可视化系统。DISCO是开源的且易于安装，它与标准文件格式兼容，并且使用门槛较低。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/493bc1285098/nihpp-2023.01.24.525459v2-f0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/05d417f21219/nihpp-2023.01.24.525459v2-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/2e24c35ed5ae/nihpp-2023.01.24.525459v2-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/8035500b9e1b/nihpp-2023.01.24.525459v2-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/b05d8e747afc/nihpp-2023.01.24.525459v2-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/cbe9aa839b56/nihpp-2023.01.24.525459v2-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/585b779fb800/nihpp-2023.01.24.525459v2-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/2f768cb9e60d/nihpp-2023.01.24.525459v2-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/c688e6a64f02/nihpp-2023.01.24.525459v2-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/1ac1a8fee3b1/nihpp-2023.01.24.525459v2-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/8698a2d57c13/nihpp-2023.01.24.525459v2-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/88592166a613/nihpp-2023.01.24.525459v2-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/12f6b83c7c77/nihpp-2023.01.24.525459v2-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/493bc1285098/nihpp-2023.01.24.525459v2-f0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/05d417f21219/nihpp-2023.01.24.525459v2-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/2e24c35ed5ae/nihpp-2023.01.24.525459v2-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/8035500b9e1b/nihpp-2023.01.24.525459v2-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/b05d8e747afc/nihpp-2023.01.24.525459v2-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/cbe9aa839b56/nihpp-2023.01.24.525459v2-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/585b779fb800/nihpp-2023.01.24.525459v2-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/2f768cb9e60d/nihpp-2023.01.24.525459v2-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/c688e6a64f02/nihpp-2023.01.24.525459v2-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/1ac1a8fee3b1/nihpp-2023.01.24.525459v2-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/8698a2d57c13/nihpp-2023.01.24.525459v2-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/88592166a613/nihpp-2023.01.24.525459v2-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/12f6b83c7c77/nihpp-2023.01.24.525459v2-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ebd7/9900853/493bc1285098/nihpp-2023.01.24.525459v2-f0013.jpg

相似文献

1
DISCO: A deep learning ensemble for uncertainty-aware segmentation of acoustic signals.DISCO：一种用于声学信号不确定性感知分割的深度学习集成方法。
bioRxiv. 2023 Jan 26:2023.01.24.525459. doi: 10.1101/2023.01.24.525459.
2
DISCO: A deep learning ensemble for uncertainty-aware segmentation of acoustic signals.深度神经网络集成模型：用于声学信号不确定性感知分割的深度学习方法
PLoS One. 2023 Jul 26;18(7):e0288172. doi: 10.1371/journal.pone.0288172. eCollection 2023.
3
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation.ORCA-SPY 使用基于集成深度学习的分割实现虎鲸声源模拟、检测、分类和定位。
Sci Rep. 2023 Jul 10;13(1):11106. doi: 10.1038/s41598-023-38132-7.
4
Silbido profundo: An open source package for the use of deep learning to detect odontocete whistles.深度哨声识别：一个用于利用深度学习检测齿鲸类口哨声的开源软件包。
J Acoust Soc Am. 2022 Dec;152(6):3800. doi: 10.1121/10.0016631.
5
TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning.TorchIO：一个用于在深度学习中高效加载、预处理、增强和基于补丁的医学图像采样的 Python 库。
Comput Methods Programs Biomed. 2021 Sep;208:106236. doi: 10.1016/j.cmpb.2021.106236. Epub 2021 Jun 17.
6
BASSA: New software tool reveals hidden details in visualisation of low-frequency animal sounds.BASSA：新软件工具揭示低频动物声音可视化中的隐藏细节。
Ecol Evol. 2024 Jul 3;14(7):e11636. doi: 10.1002/ece3.11636. eCollection 2024 Jul.
7
An open access dataset for developing automated detectors of Antarctic baleen whale sounds and performance evaluation of two commonly used detectors.用于开发南极须鲸声音自动探测器的开放获取数据集以及两种常用探测器的性能评估。
Sci Rep. 2021 Jan 12;11(1):806. doi: 10.1038/s41598-020-78995-8.
8
Multi-channel acoustic recording and automated analysis of Drosophila courtship songs.多通道声记录和自动化分析果蝇求爱歌曲。
BMC Biol. 2013 Jan 31;11:11. doi: 10.1186/1741-7007-11-11.
9
Automatic Recognition, Segmentation, and Sex Assignment of Nocturnal Asthmatic Coughs and Cough Epochs in Smartphone Audio Recordings: Observational Field Study.智能手机音频记录中夜间哮喘性咳嗽及咳嗽发作的自动识别、分割与性别判定：观察性现场研究
J Med Internet Res. 2020 Jul 14;22(7):e18082. doi: 10.2196/18082.
10
PyRaDiSe: A Python package for DICOM-RT-based auto-segmentation pipeline construction and DICOM-RT data conversion.PyRaDiSe：一个用于基于DICOM-RT的自动分割管道构建和DICOM-RT数据转换的Python软件包。
Comput Methods Programs Biomed. 2023 Apr;231:107374. doi: 10.1016/j.cmpb.2023.107374. Epub 2023 Jan 28.

本文引用的文献

1
Comparative bioacoustics: a roadmap for quantifying and comparing animal sounds across diverse taxa.比较生物声学：跨不同分类群量化和比较动物声音的路线图。
Biol Rev Camb Philos Soc. 2021 Aug;96(4):1135-1159. doi: 10.1111/brv.12695. Epub 2021 Mar 2.
2
DeepSqueak: a deep learning-based system for detection and analysis of ultrasonic vocalizations.DeepSqueak：一种基于深度学习的超声发声检测与分析系统。
Neuropsychopharmacology. 2019 Apr;44(5):859-868. doi: 10.1038/s41386-018-0303-6. Epub 2019 Jan 4.
3
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.
更快的 R-CNN：基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.
4
Pitch- and spectral-based dynamic time warping methods for comparing field recordings of harmonic avian vocalizations.基于音高和频谱的动态时间规整方法在比较鸣禽谐波叫声的野外录音中的应用。
J Acoust Soc Am. 2013 Aug;134(2):1407-15. doi: 10.1121/1.4812269.