Robust Cough Detection With Out-of-Distribution Detection
Robust Cough Detection With Out-of-Distribution Detection
复制标题
DOI：
10.1109/jbhi.2023.3264783
复制
发表时间：
2023-04
影响因子：
7.7
通讯作者：
Yuhan Chen;Pankaj Attri;J. Barahona;M. Hernandez;D. Carpenter;A. Bozkurt;E. Lobaton
中科院分区：
文献类型：
--
作者：
Yuhan Chen;Pankaj Attri;J. Barahona;M. Hernandez;D. Carpenter;A. Bozkurt;E. Lobaton
咳嗽是呼吸系统的重要防御机制，也是哮喘等肺部疾病的症状。通过便携式记录设备收集的声学咳嗽检测是跟踪哮喘患者潜在病情恶化的一种方便方法。然而，用于构建当前咳嗽检测模型的数据通常是干净的，包含一组有限的声音类别，因此当它们暴露于各种可被便携式录音设备拾取的真实声音时，表现不佳。没有被模型学习到的声音被称为out - distribution （OOD）数据。在这项工作中，我们提出了两种结合OOD检测模块的鲁棒咳嗽检测方法，在不牺牲原系统咳嗽检测性能的情况下去除OOD数据。这些方法包括增加学习置信参数和最大化熵损失。实验表明：1)在750 Hz以上的采样率下，OOD系统可以产生可靠的In-Distribution （ID）和OOD结果；2) OOD样本检测在更大的音频窗口尺寸下表现更好；3)随着OOD样本在声信号中所占比例的增加，模型的整体精度和精度越好；4)在较低采样率下，需要更高百分比的OOD数据来实现性能提升。OOD检测技术的结合大大提高了咳嗽检测性能，并为现实世界的声学咳嗽检测问题提供了有价值的解决方案。
Cough is an important defense mechanism of the respiratory system and is also a symptom of lung diseases, such as asthma. Acoustic cough detection collected by portable recording devices is a convenient way totrack potential condition worsening for patients who have asthma. However, the data used in building current cough detection models are often clean, containing a limited set of sound categories, and thus perform poorly when they are exposed to a variety of real-world sounds which could be picked up by portable recording devices. The sounds that are not learned by the model are referred to as Out-of-Distribution (OOD) data. In this work, we propose two robust cough detection methods combined with an OOD detection module, that removes OOD data without sacrificing the cough detection performance of the original system. These methods include adding a learning confidence parameter and maximizing entropy loss. Our experiments show that 1) the OOD system can produce dependable In-Distribution (ID) and OOD results at a sampling rate above 750 Hz; 2) the OOD sample detection tends to perform better for larger audio window sizes; 3) the model's overall accuracy and precision get better as the proportion of OOD samples increase in the acoustic signals; 4) a higher percentage of OOD data is needed to realize performance gains at lower sampling rates. The incorporation of OOD detection techniques improves cough detection performance by a significant margin and provides a valuable solution to real-world acoustic cough detection problems.