Obstructive Sleep Apnea (OSA) Classification Using Analysis of Breathing Sounds During Speech. Simply, R. M., Dafna, E., & Zigel, Y. In 2018 26th European Signal Processing Conference (EUSIPCO), pages 1132-1136, Sep., 2018. Paper doi abstract bibtex Obstructive sleep apnea (OSA) is a sleep disorder in which pharyngeal collapse during sleep, causes a complete or partial airway obstruction. OSA is common and can have severe impacts, but often remains unrecognized. In this study, we propose a novel method which able to detect OSA subjects while they are awake, by analyzing breathing sounds during speech. The hypothesis is that OSA is associated with anatomical and functional abnormalities of the upper airway, which in turn, affect the acoustic parameters of a natural breathing sound during speech. The proposed OSA detector is a fully automated system, which consists of three consecutive steps including: 1) locating breathing sounds during continuous speech, 2) extracting acoustic features that quantify the breathing properties, and 3) OSA/non-OSA classification based on the detected breathing sounds. Based on breathing sounds analysis alone (90 male subjects; 72 for training, 18 for validation), our system yields an encouraging results (accuracy of 76.5%) showing the potential of speech analysis to detect OSA. Such a system can be integrated with other non-contact OSA detectors to provide a reliable and OSA syndrome-screening tool.
@InProceedings{8553353,
author = {R. M. Simply and E. Dafna and Y. Zigel},
booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},
title = {Obstructive Sleep Apnea (OSA) Classification Using Analysis of Breathing Sounds During Speech},
year = {2018},
pages = {1132-1136},
abstract = {Obstructive sleep apnea (OSA) is a sleep disorder in which pharyngeal collapse during sleep, causes a complete or partial airway obstruction. OSA is common and can have severe impacts, but often remains unrecognized. In this study, we propose a novel method which able to detect OSA subjects while they are awake, by analyzing breathing sounds during speech. The hypothesis is that OSA is associated with anatomical and functional abnormalities of the upper airway, which in turn, affect the acoustic parameters of a natural breathing sound during speech. The proposed OSA detector is a fully automated system, which consists of three consecutive steps including: 1) locating breathing sounds during continuous speech, 2) extracting acoustic features that quantify the breathing properties, and 3) OSA/non-OSA classification based on the detected breathing sounds. Based on breathing sounds analysis alone (90 male subjects; 72 for training, 18 for validation), our system yields an encouraging results (accuracy of 76.5%) showing the potential of speech analysis to detect OSA. Such a system can be integrated with other non-contact OSA detectors to provide a reliable and OSA syndrome-screening tool.},
keywords = {feature extraction;medical disorders;medical signal processing;pneumodynamics;sleep;speech processing;sleep disorder;partial airway obstruction;OSA subjects;natural breathing sound;OSA detector;continuous speech;breathing properties;speech analysis;noncontact OSA detectors;reliable OSA;obstructive sleep apnea classification;OSA-nonOSA classification;breathing sound analysis;pharyngeal collapse;upper airway;acoustic feature extraction;OSA syndrome-screening tool;Feature extraction;Noise measurement;Training;Mel frequency cepstral coefficient;Signal processing;Sleep apnea;Obstructive sleep apnea (OSA);speech signals;breath signals;signal processing;machine learning},
doi = {10.23919/EUSIPCO.2018.8553353},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437038.pdf},
}
Downloads: 0
{"_id":"vKdi5WS6Y9T7qQbpr","bibbaseid":"simply-dafna-zigel-obstructivesleepapneaosaclassificationusinganalysisofbreathingsoundsduringspeech-2018","authorIDs":[],"author_short":["Simply, R. M.","Dafna, E.","Zigel, Y."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["R.","M."],"propositions":[],"lastnames":["Simply"],"suffixes":[]},{"firstnames":["E."],"propositions":[],"lastnames":["Dafna"],"suffixes":[]},{"firstnames":["Y."],"propositions":[],"lastnames":["Zigel"],"suffixes":[]}],"booktitle":"2018 26th European Signal Processing Conference (EUSIPCO)","title":"Obstructive Sleep Apnea (OSA) Classification Using Analysis of Breathing Sounds During Speech","year":"2018","pages":"1132-1136","abstract":"Obstructive sleep apnea (OSA) is a sleep disorder in which pharyngeal collapse during sleep, causes a complete or partial airway obstruction. OSA is common and can have severe impacts, but often remains unrecognized. In this study, we propose a novel method which able to detect OSA subjects while they are awake, by analyzing breathing sounds during speech. The hypothesis is that OSA is associated with anatomical and functional abnormalities of the upper airway, which in turn, affect the acoustic parameters of a natural breathing sound during speech. The proposed OSA detector is a fully automated system, which consists of three consecutive steps including: 1) locating breathing sounds during continuous speech, 2) extracting acoustic features that quantify the breathing properties, and 3) OSA/non-OSA classification based on the detected breathing sounds. Based on breathing sounds analysis alone (90 male subjects; 72 for training, 18 for validation), our system yields an encouraging results (accuracy of 76.5%) showing the potential of speech analysis to detect OSA. Such a system can be integrated with other non-contact OSA detectors to provide a reliable and OSA syndrome-screening tool.","keywords":"feature extraction;medical disorders;medical signal processing;pneumodynamics;sleep;speech processing;sleep disorder;partial airway obstruction;OSA subjects;natural breathing sound;OSA detector;continuous speech;breathing properties;speech analysis;noncontact OSA detectors;reliable OSA;obstructive sleep apnea classification;OSA-nonOSA classification;breathing sound analysis;pharyngeal collapse;upper airway;acoustic feature extraction;OSA syndrome-screening tool;Feature extraction;Noise measurement;Training;Mel frequency cepstral coefficient;Signal processing;Sleep apnea;Obstructive sleep apnea (OSA);speech signals;breath signals;signal processing;machine learning","doi":"10.23919/EUSIPCO.2018.8553353","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437038.pdf","bibtex":"@InProceedings{8553353,\n author = {R. M. Simply and E. Dafna and Y. Zigel},\n booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},\n title = {Obstructive Sleep Apnea (OSA) Classification Using Analysis of Breathing Sounds During Speech},\n year = {2018},\n pages = {1132-1136},\n abstract = {Obstructive sleep apnea (OSA) is a sleep disorder in which pharyngeal collapse during sleep, causes a complete or partial airway obstruction. OSA is common and can have severe impacts, but often remains unrecognized. In this study, we propose a novel method which able to detect OSA subjects while they are awake, by analyzing breathing sounds during speech. The hypothesis is that OSA is associated with anatomical and functional abnormalities of the upper airway, which in turn, affect the acoustic parameters of a natural breathing sound during speech. The proposed OSA detector is a fully automated system, which consists of three consecutive steps including: 1) locating breathing sounds during continuous speech, 2) extracting acoustic features that quantify the breathing properties, and 3) OSA/non-OSA classification based on the detected breathing sounds. Based on breathing sounds analysis alone (90 male subjects; 72 for training, 18 for validation), our system yields an encouraging results (accuracy of 76.5%) showing the potential of speech analysis to detect OSA. Such a system can be integrated with other non-contact OSA detectors to provide a reliable and OSA syndrome-screening tool.},\n keywords = {feature extraction;medical disorders;medical signal processing;pneumodynamics;sleep;speech processing;sleep disorder;partial airway obstruction;OSA subjects;natural breathing sound;OSA detector;continuous speech;breathing properties;speech analysis;noncontact OSA detectors;reliable OSA;obstructive sleep apnea classification;OSA-nonOSA classification;breathing sound analysis;pharyngeal collapse;upper airway;acoustic feature extraction;OSA syndrome-screening tool;Feature extraction;Noise measurement;Training;Mel frequency cepstral coefficient;Signal processing;Sleep apnea;Obstructive sleep apnea (OSA);speech signals;breath signals;signal processing;machine learning},\n doi = {10.23919/EUSIPCO.2018.8553353},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437038.pdf},\n}\n\n","author_short":["Simply, R. M.","Dafna, E.","Zigel, Y."],"key":"8553353","id":"8553353","bibbaseid":"simply-dafna-zigel-obstructivesleepapneaosaclassificationusinganalysisofbreathingsoundsduringspeech-2018","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570437038.pdf"},"keyword":["feature extraction;medical disorders;medical signal processing;pneumodynamics;sleep;speech processing;sleep disorder;partial airway obstruction;OSA subjects;natural breathing sound;OSA detector;continuous speech;breathing properties;speech analysis;noncontact OSA detectors;reliable OSA;obstructive sleep apnea classification;OSA-nonOSA classification;breathing sound analysis;pharyngeal collapse;upper airway;acoustic feature extraction;OSA syndrome-screening tool;Feature extraction;Noise measurement;Training;Mel frequency cepstral coefficient;Signal processing;Sleep apnea;Obstructive sleep apnea (OSA);speech signals;breath signals;signal processing;machine learning"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2018url.bib","creationDate":"2021-02-13T15:38:40.398Z","downloads":0,"keywords":["feature extraction;medical disorders;medical signal processing;pneumodynamics;sleep;speech processing;sleep disorder;partial airway obstruction;osa subjects;natural breathing sound;osa detector;continuous speech;breathing properties;speech analysis;noncontact osa detectors;reliable osa;obstructive sleep apnea classification;osa-nonosa classification;breathing sound analysis;pharyngeal collapse;upper airway;acoustic feature extraction;osa syndrome-screening tool;feature extraction;noise measurement;training;mel frequency cepstral coefficient;signal processing;sleep apnea;obstructive sleep apnea (osa);speech signals;breath signals;signal processing;machine learning"],"search_terms":["obstructive","sleep","apnea","osa","classification","using","analysis","breathing","sounds","during","speech","simply","dafna","zigel"],"title":"Obstructive Sleep Apnea (OSA) Classification Using Analysis of Breathing Sounds During Speech","year":2018,"dataSources":["yiZioZximP7hphDpY","iuBeKSmaES2fHcEE9"]}