METHOD AND SYSTEM FOR APPLYING SYNTHEISS VOICE TO SPEACKER IMAGES

摘要

The present disclosure relates to a method of applying synthesized speech to a speaker image, performed by at least one processor. The method includes the steps of receiving input text, inputting the input text into an artificial neural network text-to-speech synthesis model, and outputting speech data for the input text, generating a synthesized speech corresponding to the output speech data; The method may include generating information on a plurality of phonemes included in the output voice data. Here, the information on the plurality of phonemes may include timing information on each of the plurality of phonemes included in the output voice data.