School of Physics and Optoelectronics, South China University of Technology, Guangzhou, 510640, China.
State Key Laboratory of Respiratory Disease, Department of Otolaryngology-Head and Neck Surgery, Laboratory of ENT-HNS Disease, First Affiliated Hospital, Guangzhou Medical University, Guangzhou, 510120, China.
Phys Eng Sci Med. 2020 Jun;43(2):679-689. doi: 10.1007/s13246-020-00876-1. Epub 2020 May 6.
Snoring is a typical characteristic of obstructive sleep apnea hypopnea syndrome (OSAHS) and can be used for its diagnosis. The purpose of this paper is to develop an automatic snoring detection algorithm for classifying snore and non-snore sound segments, which have been segmented from a whole-night sleep sound signal using a spectral entropy method, based on convolutional neural network (CNN) descriptors extracted from audio maps. For each sound segment, the time-domain waveform, spectrum, spectrogram, Mel-spectrogram and CQT-spectrogram are calculated. Two classifiers are applied to classify sound segments into either snore or non-snore classes. The first classifier is referred to as CNNs-DNNs and combines CNNs and deep neural networks (DNNs), and the second classifier is referred to as CNNs-LSTMs-DNNs and consists of CNNs, Long and Short memory networks (LSTMs) and DNNs. The results show that the Mel-spectrogram can better reflect the differences between snore and non-snore sound segments for the five maps extracted in this study. Furthermore, the deep spectrum features extracted from CNNs-LSTMs-DNNs using Mel-spectrogram are well suited to this task. The results indicate that the method developed in this study could be used for a portable sleep monitoring device.
打鼾是阻塞性睡眠呼吸暂停低通气综合征（OSAHS）的典型特征，可用于其诊断。本文旨在开发一种基于卷积神经网络（CNN）描述符的自动打鼾检测算法，用于对使用谱熵法从全夜睡眠声音信号中分段的打鼾和非打鼾声音段进行分类。对于每个声音段，计算时域波形、频谱、语谱图、梅尔频谱图和 CQT 频谱图。应用两种分类器将声音段分类为打鼾或非打鼾类别。第一个分类器称为 CNNs-DNNs，它结合了 CNN 和深度神经网络（DNNs），第二个分类器称为 CNNs-LSTMs-DNNs，由 CNN、长短时记忆网络（LSTMs）和 DNNs 组成。结果表明，对于本研究中提取的五个图谱，梅尔频谱图可以更好地反映打鼾和非打鼾声音段之间的差异。此外，使用梅尔频谱图从 CNNs-LSTMs-DNNs 中提取的深度频谱特征非常适合这项任务。结果表明，本研究中开发的方法可用于便携式睡眠监测设备。
