Xie Jiali, Aubert Xavier, Long Xi, van Dijk Johannes, Arsenali Bruno, Fonseca Pedro, Overeem Sebastiaan
Biomedical Diagnostics Group, Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands.
Biomedical Diagnostics Group, Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands; Philips Research, High Tech Campus, 5656 AE Eindhoven, The Netherlands.
Comput Methods Programs Biomed. 2021 Mar;200:105917. doi: 10.1016/j.cmpb.2020.105917. Epub 2020 Dec 25.
Snoring is a prevalent phenomenon. It may be benign, but can also be a symptom of obstructive sleep apnea (OSA) a prevalent sleep disorder. Accurate detection of snoring may help with screening and diagnosis of OSA.
We introduce a snore detection algorithm based on the combination of a convolutional neural network (CNN) and a recurrent neural network (RNN). We obtained audio recordings of 38 subjects referred to a clinical center for a sleep study. All subjects were recorded by a total of 5 microphones placed at strategic positions around the bed. The CNN was used to extract features from the sound spectrogram, while the RNN was used to process the sequential CNN output and to classify the audio events to snore and non-snore events. We also addressed the impact of microphone placement on the performance of the algorithm.
The algorithm achieved an accuracy of 95.3 ± 0.5%, a sensitivity of 92.2 ± 0.9%, and a specificity of 97.7 ± 0.4% over all microphones in snore detection on our data set including 18412 sound events. The best accuracy (95.9%) was observed from the microphone placed about 70 cm above the subject's head and the worst (94.4%) was observed from the microphone placed about 130 cm above the subject's head.
Our results suggest that our method detects snore events from audio recordings with high accuracy and that microphone placement does not have a major impact on detection performance.
打鼾是一种普遍现象。它可能是良性的，但也可能是阻塞性睡眠呼吸暂停（OSA）这一常见睡眠障碍的症状。准确检测打鼾可能有助于阻塞性睡眠呼吸暂停的筛查与诊断。
我们介绍一种基于卷积神经网络（CNN）和循环神经网络（RNN）相结合的打鼾检测算法。我们获取了38名前往临床中心进行睡眠研究的受试者的音频记录。所有受试者均由放置在床周围关键位置的5个麦克风进行记录。CNN用于从声谱图中提取特征，而RNN用于处理CNN的序列输出，并将音频事件分类为打鼾和非打鼾事件。我们还探讨了麦克风放置对算法性能的影响。
在我们包含18412个声音事件的数据集上，该算法在打鼾检测中对所有麦克风实现了95.3±0.5%的准确率、92.2±0.9%的灵敏度和97.7±0.4%的特异性。在受试者头部上方约70厘米处放置的麦克风观察到最佳准确率（95.9%），在受试者头部上方约130厘米处放置的麦克风观察到最差准确率（94.4%）。
我们的结果表明，我们的方法能从音频记录中高精度地检测打鼾事件，并且麦克风放置对检测性能没有重大影响。
