LEARNING DEVICE LEARNING METHOD DEVICE AND METHOD FOR VALID UTTERANCE RECOGNITION

摘要

According to an embodiment of the present invention, it includes a memory for storing one or more instructions and at least one processor executing the one or more instructions, wherein the at least one processor includes information on whether or not a valid utterance is tagged (tagging). Generates first information on a contextual characteristic of the at least one input sequence based on the at least one input sequence, and determines whether the generated first information and the tagged valid utterance Train a neural network based on information.