File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Optimal vowels measurements for Obstructive Sleep Apnea Detection Using Speech Signals

TitleOptimal vowels measurements for Obstructive Sleep Apnea Detection Using Speech Signals
Authors
KeywordsObstructive Sleep Apnea
speech analysis
Linear Predictive coder (LPC)
machine learning
Issue Date2020
PublisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1828505/all-proceedings
Citation
2020 the 3rd IEEE International Conference on Information Communication and Signal Processing (ICICSP 2020), Shanghai, China, 12-15 September 2020, p. 143-147 How to Cite?
AbstractIn Obstructive Sleep Apnea (OSA) detection using speech signal during awake, traditional speech-based methods adopt speech features such as Formants and MFCC. As the OSA voice is pathological, the parameters for normal speech processing/recognition is not optimal for the detection. In this paper, we investigate the effects of Linear Predictive coder (LPC) order to the OSA detection. We further propose to adopt dual LPC for feature extractions. In the simulation using 66 OSA patients' voice signals, we achieve the best accuracy of 95.45% and 86.36% with the proposed parameters using quadratic discriminant analysis classifier for multi-class (4 levels) OSA severity classification using resubstitution and leave-one-out method respectively. As compared to the typical parameters setting, the improvement of resubstitution and leave-one-out are 6.06% and 9.09% respectively.
Persistent Identifierhttp://hdl.handle.net/10722/289183
ISBN

 

DC FieldValueLanguage
dc.contributor.authorPang, KG-
dc.contributor.authorHsung, TC-
dc.contributor.authorLaw, AKW-
dc.contributor.authorChoi, WWS-
dc.date.accessioned2020-10-22T08:09:01Z-
dc.date.available2020-10-22T08:09:01Z-
dc.date.issued2020-
dc.identifier.citation2020 the 3rd IEEE International Conference on Information Communication and Signal Processing (ICICSP 2020), Shanghai, China, 12-15 September 2020, p. 143-147-
dc.identifier.isbn978-1-7281-8824-9-
dc.identifier.urihttp://hdl.handle.net/10722/289183-
dc.description.abstractIn Obstructive Sleep Apnea (OSA) detection using speech signal during awake, traditional speech-based methods adopt speech features such as Formants and MFCC. As the OSA voice is pathological, the parameters for normal speech processing/recognition is not optimal for the detection. In this paper, we investigate the effects of Linear Predictive coder (LPC) order to the OSA detection. We further propose to adopt dual LPC for feature extractions. In the simulation using 66 OSA patients' voice signals, we achieve the best accuracy of 95.45% and 86.36% with the proposed parameters using quadratic discriminant analysis classifier for multi-class (4 levels) OSA severity classification using resubstitution and leave-one-out method respectively. As compared to the typical parameters setting, the improvement of resubstitution and leave-one-out are 6.06% and 9.09% respectively.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1828505/all-proceedings-
dc.relation.ispartofIEEE International Conference on Information, Communication and Signal Processing (ICICSP)-
dc.rightsIEEE International Conference on Information, Communication and Signal Processing (ICICSP). Copyright © IEEE.-
dc.rights©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectObstructive Sleep Apnea-
dc.subjectspeech analysis-
dc.subjectLinear Predictive coder (LPC)-
dc.subjectmachine learning-
dc.titleOptimal vowels measurements for Obstructive Sleep Apnea Detection Using Speech Signals-
dc.typeConference_Paper-
dc.identifier.emailChoi, WWS: drwchoi@hku.hk-
dc.identifier.authorityChoi, WWS=rp01521-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICICSP50920.2020.9231972-
dc.identifier.hkuros317355-
dc.identifier.spage143-
dc.identifier.epage147-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats