Sound Dr Dataset

As the burden of respiratory diseases continues to fall on society worldwide, this paper proposes a high-quality and robust dataset of human sounds for studying respiratory illnesses, including pneumonia and COVID-19. It consists of coughing, mouth breathing, and nose breathing sounds together with valuable metadata on related clinical characteristics. We also develop a proof-of-concept system for establishing baselines and benchmarking against multiple datasets, such as Coswara and COUGHVID. Our comprehensive experiments show that the Sound-Dr dataset has richer features, better performance, and is more robust to dataset shifts in various machine learning tasks. It is promising for a wide range of real-time applications on mobile devices. The proposed dataset and system will serve as practical tools to support healthcare professionals in diagnosing respiratory disorders. The dataset and code are publicly available here: https://github.com/hvt1609/Sound-Dr-dataset.git.

随着全球呼吸道疾病给社会造成的负担持续攀升，本文提出了一款用于呼吸道疾病（涵盖肺炎与新型冠状病毒肺炎（COVID-19））研究的高质量、高鲁棒性人体声音数据集。该数据集包含咳嗽、经口呼吸与经鼻呼吸音频，以及涵盖相关临床特征的高价值元数据。我们还开发了一套概念验证系统，可用于构建基准基线，并与Coswara、COUGHVID等多个数据集开展基准测试对比。我们的全面实验结果表明，Sound-Dr数据集拥有更丰富的特征、更优异的模型表现，且在各类机器学习任务中对数据集偏移（dataset shifts）具备更强的鲁棒性。该数据集在移动设备的各类实时应用场景中具备广阔的应用前景。本研究提出的数据集与配套系统将作为实用工具，为医疗专业人员开展呼吸道病症诊断提供支持。本数据集及代码已通过以下链接公开获取：https://github.com/hvt1609/Sound-Dr-dataset.git。