SPEECH TRANSLATION METHOD AND SYSTEM USING MULTILINGUAL TEXT-TO-SPEECH SYNTHESIS MODEL

摘要

The present disclosure relates to a speech translation method or system using a multilingual text-to-speech synthesis model. A speech translation method using a multilingual text-to-speech synthesis model comprises the steps of: acquiring a single artificial neural network text-to-speech synthesis model having acquired learning on the basis of learning text of a first language and learning speech data of the first language corresponding to the learning text of the first language and, learning text of a second language and learning speech data of the second language corresponding to the learning text of the second language; receiving input speech data of the first language and an utterer's articulatory characteristics in the first language; converting the input speech data of the first language into text of the first language; converting the text of the first language into text of the second language; and generating output speech data which corresponds to the text of the second language and replicates the utterer's speech, by inputting the text of the second language and the utterer's articulatory characteristics to a single artificial neural network text-to-speech synthesis model.