Automatic Detection of Whole Night Snoring Events Using Non-Contact Microphone

Abstract

ObjectiveAlthough awareness of sleep disorders is increasing, limited information is available on whole night detection of snoring. Our study aimed to develop and validate a robust, high performance, and sensitive whole-night snore detector based on non-contact technology.DesignSounds during polysomnography (PSG) were recorded using a directional condenser microphone placed 1 m above the bed. An AdaBoost classifier was trained and validated on manually labeled snoring and non-snoring acoustic events.PatientsSixty-seven subjects (age 52.5±13.5 years, BMI 30.8±4.7 kg/m2, m/f 40/27) referred for PSG for obstructive sleep apnea diagnoses were prospectively and consecutively recruited. Twenty-five subjects were used for the design study; the validation study was blindly performed on the remaining forty-two subjects.Measurements and ResultsTo train the proposed sound detector, >76,600 acoustic episodes collected in the design study were manually classified by three scorers into snore and non-snore episodes (e.g., bedding noise, coughing, environmental). A feature selection process was applied to select the most discriminative features extracted from time and spectral domains. The average snore/non-snore detection rate (accuracy) for the design group was 98.4% based on a ten-fold cross-validation technique. When tested on the validation group, the average detection rate was 98.2% with sensitivity of 98.0% (snore as a snore) and specificity of 98.3% (noise as noise).ConclusionsAudio-based features extracted from time and spectral domains can accurately discriminate between snore and non-snore acoustic events. This audio analysis approach enables detection and analysis of snoring sounds from a full night in order to produce quantified measures for objective follow-up of patients.

Breathing and Snoring Sound Characteristics during Sleep in Adults

“…[1][2][3][4][5][6][7] Inspiratory breathing sounds can vary significantly across sleep and between subjects; in some cases the sounds may be soft (sound intensity < 40 dB), but in others it can be loud. [8][9][10][11][12][13][14][15][16] Intense breathing sounds are commonly referred to as snoring. 10,[13][14][15][16] The most accepted estimate for the prevalence of chronic snoring is 40% in adult men and 20% in adult women, although the variability is extremely large.…”

“…[8][9][10][11][12][13][14][15][16] Intense breathing sounds are commonly referred to as snoring. 10,[13][14][15][16] The most accepted estimate for the prevalence of chronic snoring is 40% in adult men and 20% in adult women, although the variability is extremely large. 16 Early work has shown a poor correlation between measured loudness of snoring and subjective appreciation by different observers.…”

“…14 Several studies have addressed the issue of detection of snoring sounds from a recorded audio signal during sleep using signal processing and pattern recognition algorithms. 10,[17][18][19][20][21][22][23] Recently, we showed that audio-based features, extracted from audio recordings, can accurately detect, not only snoring sounds, but also sleep breathing sound events (intensity > 20 dB) even in a very quiet environment, with accuracy > 98%. 10 We also found that more than 97% of the snoring events occurred during inspiration; expiratory sound events are not common, confirming earlier reports.…”

“…10,[17][18][19][20][21][22][23] Recently, we showed that audio-based features, extracted from audio recordings, can accurately detect, not only snoring sounds, but also sleep breathing sound events (intensity > 20 dB) even in a very quiet environment, with accuracy > 98%. 10 We also found that more than 97% of the snoring events occurred during inspiration; expiratory sound events are not common, confirming earlier reports. 9,21 This approach of detection of breathing sounds was further validated to reliably estimate apnea-hypopnea index (AHI) 24 and sleep-wake activity 25 in laboratory and at-home environments.…”

“…during sleep, from the time and frequency domain, using a validated approach that enables discrimination between inspiratory breathing and snoring sounds (the signal of interest) and other sounds (noise events). 10 Here, we analyzed the effect of sex, OSA severity, and sleep stages on the feature characteristics of inspiratory breathing and snoring sounds during wholenight polysomnography (PSG).…”