METHOD AND APPARATUS FOR VOICE TRANSLATION USING A MULTILINGUAL TEXT-TO-SPEECH SYNTHESIS MODEL

摘要

The present disclosure relates to a speech translation method, a video translation method, or a system using a multilingual text-to-speech synthesis model. A speech translation method using a multilingual text-to-speech synthesis model includes learning text of a first language and learning voice data of a first language corresponding to the learning text of the first language, learning text of a second language, and learning of a second language Acquiring a single artificial neural network text-to-speech synthesis model learned based on learning speech data of a second language corresponding to text; receiving speech characteristics of a speaker, converting input speech data in a first language to text in a first language, converting text in the first language to text in a second language, and text in the second language and and inputting the speaker's speech characteristics into a single artificial neural network text-to-speech synthesis model to generate output speech data for text in a second language that mimics the speaker's speech.