Apparatus and method for generating lip sync image

A method for generating a lip sync image performed by a computing device having one or more processors and a memory which stores one or more programs executed by the one or more processors, the method comprising:

• generating, in a first artificial neural network model, an utterance synthesis image by using a person background image and an utterance audio signal corresponding to the person background image as an input;
• generating, in the first artificial neural network model, a silence synthesis image by using only the person background image as an input;
• and
• outputting, in a second artificial neural network model, classification values for a preset utterance maintenance image and the silence synthesis image by using the preset utterance maintenance image and the silence synthesis image as an input,
• wherein the utterance maintenance image is an image in which the utterance movement of the person is constant, and the silence synthesis image is a lip sync image generated only with the person background image without an audio signal,
• wherein the second artificial neural network model is trained to classify the utterance maintenance image as True, and to classify the silence synthesis image as False.