METHOD AND APPARTUS FOR VOICE CONVERSION BY USING NEURAL NETWORK

摘要

According to an embodiment of the present disclosure, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed in one or more processors, it performs the following operations for converting a voice using a neural network, wherein the operation includes first voice characteristic information obtained by inputting an input voice to a voice feature extracting unit, or obtaining video-audio characteristic information, which is audio characteristic information synchronized with the input image, based on at least one of the image characteristic information obtained by inputting the input image to the image characteristic extraction unit; and inputting the video-audio characteristic information to a voice converter trained to reconstruct the voice of the specific speaker, and converting the input voice into a voice reflecting the voice characteristics of the specific speaker.