An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN
Page view(s)
30
Checked on Jan 11, 2025
An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN
An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN
Nwe, T.L., Tran, H.D., Ng, W.Z.T., Ma, B. (2017) An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance Based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN. Proc. Interspeech 2017, 3467-3471, DOI: 10.21437/Interspeech.2017-1794.
Abstract:
Snoring is caused by the narrowing of the upper airway and it is excited by different locations within the upper airways. This irregularity could lead to the presence of Obstructive Sleep Apnea Syndrome (OSAS). Diagnosis of OSAS could therefore be made by snoring sound analysis. This paper proposes the novel method to automatically classify snoring sounds by their excitation locations for ComParE2017 challenge. We propose
3 sub-systems for classification. In the first system, we propose to integrate Bhattacharyya distance based Gaussian Mixture Model (GMM) supervectors to a set of static features provided by ComParE2017 challenge. The Bhattacharyya distance based GMM supervectors characterize the spectral dissimilarity measure among snore sounds excited by different locations. And, we employ Support Vector Machine (SVM) for classification.
In the second system, we perform feature selection on static features provided by the challenge and conduct classification using Random Forest. In the third system, we extract spectrogram from audio and employ Convolutional Neural Network (CNN) for snore sound classification. Then, we fuse 3 sub-systems to produce final classification results. The experimental results show that the proposed system performs better than the challenge baseline.