VOICE CONVERSION DEVICE, VOICE CONVERSION LEARNING DEVICE, IMAGE GENERATION DEVICE, IMAGE GENERATION LEARNING DEVICE, VOICE CONVERSION METHOD, VOICE CONVERSION LEARNING METHOD, IMAGE GENERATION METHOD, IMAGE GENERATION LEARNING METHOD, AND COMPUTER PROGRAM

摘要

This voice conversion device comprises a language information extraction unit that extracts language information corresponding to speech content from a voice signal of a conversion source, an appearance feature extraction unit that extracts an appearance feature representing a feature of a person's face from a captured image in which the person is imaged, and a converted voice generation unit that generates a post-conversion voice on the basis of the language information and the appearance feature.