Unsupervised snore detection from respiratory sound signals

Acoustic monitoring and diagnosis of Obstructive Sleep Apnea (OSA) has attracted increasing attentions recently due to its advantages over traditional Polysomnography (PSG) based diagnosis. The performances of several existing approaches are often limited by several aspects such as large amount of training data and and high computational cost. In this paper, we proposed a novel snore detection method utilizing the Vertical Box (V-Box) algorithm to detect snore candidate, and then we calculate the spectral feature Mel-Frequency Cepstral Coefficients (MFCCs) of each candidate. Finally, K-Harmonic Means (KHM) clustering algorithm are used to achieve the general classification decision (snore or non-snore). Experimental results demonstrate that the overall accuracy of our proposed method is 95.6% with Positive Predictive Value (PPV) 96.0%, which is superior to the existing approaches.

[1]  Ansgar Steland,et al.  Nonparametric Sequential Change-Point Detection by a Vertically Trimmed Box Method , 2010, IEEE Transactions on Information Theory.

[2]  Takahiko Ono,et al.  The calculation of sleep apnea syndorome’s condition index using the snore noise , 2006 .

[3]  P D Hill,et al.  A simple audio data logger for objective assessment of snoring in the home. , 1999, Physiological measurement.

[4]  V. Hoffstein,et al.  Apnea and snoring: state of the art and future directions. , 2002, Acta oto-rhino-laryngologica Belgica.

[5]  R. Chervin,et al.  Sleepiness, fatigue, tiredness, and lack of energy in obstructive sleep apnea. , 2000, Chest.

[6]  L. Findley,et al.  Habitually sleepy drivers have a high frequency of automobile crashes associated with respiratory disorders during sleep. , 2000, American journal of respiratory and critical care medicine.

[7]  Samuel Kim,et al.  A pitch synchronous feature extraction method for speaker recognition , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Ronald M. Aarts,et al.  The acoustics of snoring. , 2010, Sleep medicine reviews.

[9]  M Cavusoglu,et al.  An efficient method for snore/nonsnore classification of sleep sounds , 2007, Physiological measurement.

[10]  I Schnittger,et al.  Upper airway resistance syndrome, nocturnal blood pressure monitoring, and borderline hypertension. , 1996, Chest.

[11]  W D Duckitt,et al.  Automatic detection, segmentation and assessment of snoring from ambient acoustic data. , 2006, Physiological measurement.

[12]  Umeshwar Dayal,et al.  K-Harmonic Means - A Data Clustering Algorithm , 1999 .

[13]  Reinhold Häb-Umbach,et al.  An investigation of cepstral parameterisations for large vocabulary speech recognition , 1999, EUROSPEECH.

[14]  Zahra Moussavi,et al.  Automatic and Unsupervised Snore Sound Extraction From Respiratory Sound Signals , 2011, IEEE Transactions on Biomedical Engineering.

[15]  Yaniv Zigel,et al.  Automatic detection of snoring events using Gaussian mixture models , 2011, MAVEBA.

[16]  Bin Zhang.  Generalized K-Harmonic Means -- Boosting in Unsupervised Learning , 2000 .