A Dual Source-Filter Model of Snore Audio for Snorer Group Classification

Snoring is a common symptom of serious chronic disease known as obstructive sleep apnea (OSA). Knowledge about the location of obstruction site (VVelum, OOropharyngeal lateral walls, T-Tongue, E-Epiglottis) in the upper airways is necessary for proper surgical treatment. In this paper we propose a dual source-filter model similar to the source-filter model of speech to approximate the generation process of snore audio. The first filter models the vocal tract from lungs to the point of obstruction with white noise excitation from the lungs. The second filter models the vocal tract from the obstruction point to the lips/nose with impulse train excitation which represents vibrations at the point of obstruction. The filter coefficients are estimated using the closed and open phases of the snore beat cycle. VOTE classification is done by using SVM classifier and filter coefficients as features. The classification experiments are performed on the development set (283 snore audios) of the MUNICH-PASSAU SNORE SOUND CORPUS (MPSSC). We obtain an unweighted average recall (UAR) of 49.58%, which is higher than the INTERSPEECH-2017 snoring sub-challenge baseline technique by ∼3% (absolute).