Abstract: A computing system for a plurality of classes of audio events is provided, including one or more processors configured to divide a run-time audio signal into a plurality of segments and process each segment of the run-time audio signal in a time domain to generate a normalized time domain representation of each segment. The processor is further configured to feed the normalized time domain representation of each segment to an input layer of a trained neural network. The processor is further configured to generate, by the neural network, a plurality of predicted classification scores and associated probabilities for each class of audio event contained in each segment of the run-time input audio signal. In post-processing, the processor is further configured to generate smoothed predicted classification scores, associated smoothed probabilities, and class window confidence values for each class for each of a plurality of candidate window sizes.

Abstract: Devices for popping corn can include a pot, a lid assembly configured to mate with the pot, and an agitator assembly configured to be positioned within an interior volume of the pot, and to releasably engage the lid assembly when the lid assembly is mated with the pot. The agitator assembly can include at least one blade configured to cause un-popped kernels of corn within the pot to tumble as the agitator assembly is rotated within the pot, to help prevent sticking and burning of the kernels. The agitator assembly also can include at least one arm that transmits torque to the blade. The arm can be offset laterally from the axis of rotation of the agitator assembly.