肺部的音频数据集

1.  数据集介绍

1.1 COUGHVID

https://paperswithcode.com/dataset/coughvid;
https://zenodo.org/record/7024894

COUGHVID 数据集提供了 20,000 多个众包​​咳嗽录音,代表了广泛的受试者年龄、性别、地理位置和 COVID-19 状态。首先,使用开源咳嗽检测算法对数据集进行过滤。其次,经验丰富的肺科医生标记了 2000 多个录音,以诊断咳嗽中存在的医学异常,从而贡献了现有最大的专家标记咳嗽数据集之一,可用于大量咳嗽音频分类任务。

对应的项目介绍:

https://github.com/skanderhamdi/attention_cnn_lstm_covid_mel_spectrogram

1.2 语谱图呼吸音

Spectrogram Images of Breathing Sounds for COVID-19 and other Pulmonary Abnormalities

https://data.mendeley.com/datasets/pr7bgzxpgv/1

需要注意的是,该数据集是并非原始的音频数据,
而是呼吸音的语谱图形式;

该数据集包含真实和生成的人类呼吸声音的频谱图图像。真实的呼吸声来自 Covid-19 患者以及未受 Covid-19 影响的人(正常人)。生成的呼吸音是从在线医学存储库中获取的,用于教育目的。呼吸音分为 4 类:粗爆裂声、细爆裂声、喘息声和正常。

1.3 Cambridge University cov19

https://www.covid-19-sounds.org/en/

Three datasets (KDD-data, ComParE2021-CCS-CSS-Data, and NeurlPs2021-data) have been collected from the University of Cambridge for research purposes with the mutual agreement;

对应的项目介绍:

https://github.com/HrithikNambiar/COVID-19-Cough-Detection;
https://github.com/cam-mobsys/covid19-sounds-neurips

对应的文章介绍

https://www.sciencedirect.com/science/article/pii/S1110016821003859?via%3Dihub;

对应的文章介绍
COVID-19: respiratory disease diagnosis with regularized deep convolutional neural network using human respiratory sounds

COVID-19 disease diagnosis with light-weight CNN using modified MFCC and enhanced GFCC from human respiratory sounds

猜你喜欢

转载自blog.csdn.net/chumingqian/article/details/131362313