Apparatus and method for generating speech synthesis image

A method for generating a speech synthesis image based on machine learning that is performed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors, the method comprising:

• training a first global geometric transformation predictor to receive each of a source image and a target image including the same person, and predict a global geometric transformation for a global motion of the person between the source image and the target image, based on the source image and the target image;
• training a local geometric transformation predictor to predict a local geometric transformation for a local motion of the person between the source image and the target image, based on preset input data;
• calculating, in a geometric transformation combiner, a full motion geometric transformation for a full motion of the person by combining the global geometric transformation and the local geometric transformation;
• training an optical flow predictor to calculate an optical flow between the source image and the target image, based on the source image and the full motion geometric transformation;
• and
• training an image generator to reconstruct the target image, based on the source image and the optical flow,
• wherein the training of the first global geometric transformation predictor comprises:
• extracting a geometric transformation into a source image heat map from a preset reference probability distribution, based on the source image;
• extracting a geometric transformation into a target image heat map from the preset reference probability distribution, based on the target image;
• and
• calculating the global geometric transformation, based on the geometric transformation into the source image heat map from the reference probability distribution and the geometric transformation into the target image heat map from the reference probability distribution.