Snoring Sound Recognition Using Multi-Channel Spectrograms

Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common and high-risk sleep-related breathing disorder. Snoring detection is a simple and non-invasive method. In many studies, the feature maps are obtained by applying a short-time Fourier transform (STFT) and feeding the model with single-chan...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziqiang YE, Jianxin PENG, Xiaowen ZHANG, Lijuan SONG
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2024-01-01
Series:Archives of Acoustics
Subjects:
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/3807
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413842197544960
author Ziqiang YE
Jianxin PENG
Xiaowen ZHANG
Lijuan SONG
author_facet Ziqiang YE
Jianxin PENG
Xiaowen ZHANG
Lijuan SONG
author_sort Ziqiang YE
collection DOAJ
description Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common and high-risk sleep-related breathing disorder. Snoring detection is a simple and non-invasive method. In many studies, the feature maps are obtained by applying a short-time Fourier transform (STFT) and feeding the model with single-channel input tensors. However, this approach may limit the potential of convolutional networks to learn diverse representations of snore signals. This paper proposes a snoring sound detection algorithm using a multi-channel spectrogram and convolutional neural network (CNN). The sleep recordings from 30 subjects at the hospital were collected, and four different feature maps were extracted from them as model input, including spectrogram, Mel-spectrogram, continuous wavelet transform (CWT), and multi-channel spectrogram composed of the three single-channel maps. Three methods of data set partitioning are used to evaluate the performance of feature maps. The proposed feature maps were compared through the training set and test set of independent subjects by using a CNN model. The results show that the accuracy of the multi-channel spectrogram reaches 94.18%, surpassing that of the Mel-spectrogram that exhibits the best performance among the single-channel spectrograms. This study optimizes the system in the feature extraction stage to adapt to the superior feature learning capability of the deep learning model, providing a more effective feature map for snoring detection.
format Article
id doaj-art-8b30ab83b09949daa55108fc33e73471
institution Kabale University
issn 0137-5075
2300-262X
language English
publishDate 2024-01-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-8b30ab83b09949daa55108fc33e734712025-08-20T03:34:00ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2024-01-0149210.24425/aoa.2024.148775Snoring Sound Recognition Using Multi-Channel SpectrogramsZiqiang YE0Jianxin PENG1Xiaowen ZHANG2Lijuan SONG3South China University of TechnologySouth China University of TechnologyGuangzhou Medical UniversityGuangzhou Medical UniversityObstructive sleep apnea-hypopnea syndrome (OSAHS) is a common and high-risk sleep-related breathing disorder. Snoring detection is a simple and non-invasive method. In many studies, the feature maps are obtained by applying a short-time Fourier transform (STFT) and feeding the model with single-channel input tensors. However, this approach may limit the potential of convolutional networks to learn diverse representations of snore signals. This paper proposes a snoring sound detection algorithm using a multi-channel spectrogram and convolutional neural network (CNN). The sleep recordings from 30 subjects at the hospital were collected, and four different feature maps were extracted from them as model input, including spectrogram, Mel-spectrogram, continuous wavelet transform (CWT), and multi-channel spectrogram composed of the three single-channel maps. Three methods of data set partitioning are used to evaluate the performance of feature maps. The proposed feature maps were compared through the training set and test set of independent subjects by using a CNN model. The results show that the accuracy of the multi-channel spectrogram reaches 94.18%, surpassing that of the Mel-spectrogram that exhibits the best performance among the single-channel spectrograms. This study optimizes the system in the feature extraction stage to adapt to the superior feature learning capability of the deep learning model, providing a more effective feature map for snoring detection.https://acoustics.ippt.pan.pl/index.php/aa/article/view/3807obstructive sleep apnea-hypopnea syndromesnoringconvolutional neural networkmulti-channel spectrogram
spellingShingle Ziqiang YE
Jianxin PENG
Xiaowen ZHANG
Lijuan SONG
Snoring Sound Recognition Using Multi-Channel Spectrograms
Archives of Acoustics
obstructive sleep apnea-hypopnea syndrome
snoring
convolutional neural network
multi-channel spectrogram
title Snoring Sound Recognition Using Multi-Channel Spectrograms
title_full Snoring Sound Recognition Using Multi-Channel Spectrograms
title_fullStr Snoring Sound Recognition Using Multi-Channel Spectrograms
title_full_unstemmed Snoring Sound Recognition Using Multi-Channel Spectrograms
title_short Snoring Sound Recognition Using Multi-Channel Spectrograms
title_sort snoring sound recognition using multi channel spectrograms
topic obstructive sleep apnea-hypopnea syndrome
snoring
convolutional neural network
multi-channel spectrogram
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/3807
work_keys_str_mv AT ziqiangye snoringsoundrecognitionusingmultichannelspectrograms
AT jianxinpeng snoringsoundrecognitionusingmultichannelspectrograms
AT xiaowenzhang snoringsoundrecognitionusingmultichannelspectrograms
AT lijuansong snoringsoundrecognitionusingmultichannelspectrograms