In this paper, a novel algorithm is proposed for automatic detection of snoring sounds from ambient acoustic data in a pediatric population. With the approval of institutional ethic committee and parents, the respiratory sounds of 50 subjects were recorded by using a pair of microphones and multichannel data acquisition system simultaneously with full-night polysomnography during sleep. Brief sound chunks of 0.5 s were classified as either belonging to a snoring event or not with a multi-layer perceptron which was trained in a supervised fashion using stochastic gradient descent on a large hand-labeled dataset using frequency domain features. The overall accuracy of the proposed algorithm was found to be 88.93% for primary snorers and 80.6% for obstructive sleep apnea (OSA) patients.