VOICE RECOGNITION METHOD, VOICE RECOGNITION DEVICE, DEVICE HAVING VOICE RECOGNITION DEVICE, STORAGE MEDIUM STORING PROGRAM FOR PERFORMING VOICE RECOGNITION METHOD, AND METHOD FOR GENERATING CONVERSION MODEL

摘要

According to an embodiment of the present invention, provided are a voice recognition method capable of more effectively recognizing a voice, a voice recognition device, a device having the voice recognition device, a storage medium for storing a program for performing the voice recognition method, and a method for generating a conversion model. According to an embodiment of the present invention, the voice recognition method comprises the steps of: generating a second audio signal by pre-processing a first audio signal; extracting a feature point of the second audio signal, and converting the feature point by using a conversion model so as to convert the second audio signal into a third audio signal; and outputting a recognition result by applying a recognition model to the third signal.;COPYRIGHT KIPO 2018