METHOD, DEVICE, AND COMPUTER READABLE STORAGE MEDIUM FOR PERFORMING TEXT-TO-SPEECH SYNTHESIS USING MACHINE LEARNING BASED ON SEQUENTIAL PROSODY FEATURE

摘要

The present disclosure relates to a method for text-to-speech synthesis using machine learning based on a sequential prosody feature. The method capable of more accurately conveying intention or emotion of a person through speech synthesis comprises the steps of: receiving an input text; receiving a sequential prosody feature; and inputting the input text and receive sequential prosody feature into an artificial neural network text-to-speech synthesis model to generate output speech data with respect to the input text in which the sequential prosody feature is reflected.;COPYRIGHT KIPO 2020