Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 3
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

This paper proposes a comprehensive study on machine listening for localisation of snore sound excitation. Here we investigate the effects of varied frame sizes, and overlap of the analysed audio chunk for extracting low-level descriptors. In addition, we explore the performance of each kind of feature when it is fed into varied classifier models, including support vector machines, k-nearest neighbours, linear discriminant analysis, random forests, extreme learning machines, kernel-based extreme learning machines, multilayer perceptrons, and deep neural networks. Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.

Go to article

Authors and Affiliations

Qian Kun
Christoph Janott
Zhang Zixing
Deng Jun
Alice Baird
Heiser Clemens
Winfried Hohenhorst
Michael Herzog
Hemmert Werner
Björn Schuller
Download PDF Download RIS Download Bibtex

Abstract

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.
Go to article

Authors and Affiliations

Ziqiang Ye
1
Jianxin Peng
2
Xiaowen Zhang
3
Lijuan Song
3

  1. School of Physics and Optoelectronics, South China University of Technology Guangzhou, China`
  2. School of Physics and Optoelectronics, South China University of Technology Guangzhou, China
  3. State Key Laboratory of Respiratory Disease, Department of Otolaryngology-Head and Neck Surgery
Download PDF Download RIS Download Bibtex

Abstract

Obstructive sleep apnea hypopnea syndrome (OSAHS) is a prevalent and detrimental chronic condition. The conventional diagnostic approach for OSAHS is intricate and costly. Snoring is one of the most typical and easily obtained symptom of OSAHS patients. In this study, a series of acoustic features are extracted from snoring sounds. A fused model that integrates a deep neural network, K-nearest neighbors (KNN), and a random under sampling boost algorithm is proposed to classify snoring sounds of simple snorers (SSSS), simple snoring sounds of OSAHS patients (SSSP), and apnea-hypopnea snoring sounds of OSAHS patients (APSP). The ReliefF algorithm is employed to select features with high relevance in each classification model. A hard voting strategy is implemented to obtain an optimal fused model. Results show that the proposed fused model achieves commendable performance with an accuracy rate of 85.76%. It demonstrates the effectiveness and validity of assisting in diagnosing OSAHS patients based on the analysis of snoring sounds.
Go to article

Authors and Affiliations

Yexin Luo
1
Jianxin Peng
1
Li Ding
2
Yikai Zhang
1
Lijuan Song
3
Qianfan Zhang
1
Houpeng Chen
1

  1. School of Physics and Optoelectronics, South China University of Technology Guangzhou, China
  2. School of Advanced Manufacturing Engineering, Hefei University Hefei, China
  3. 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, China

This page uses 'cookies'. Learn more