Speech synthesis model training method and device, computer equipment and storage medium

Abstract

The invention relates to a speech synthesis model training method. The method comprises the steps of obtaining training text data and training speech features corresponding to the training text data;obtaining training phoneme data corresponding to the training text data according to the training text data; and taking the training text data and the training phoneme data as input of a speech synthesis model, and taking training speech features corresponding to the training text data as expected output of the speech synthesis model to train the speech synthesis model to obtain a target speech synthesis model. The training text data and the training phoneme data serve as input of the speech synthesis model at the same time, a training data set for training the speech synthesis model is enriched, and the quality and accuracy of synthesized speech are improved. In addition, the invention further provides a voice synthesis model training device, computer equipment and a storage medium.

Description

technical field [0001] The invention relates to the field of computer processing, in particular to a training method, device, computer equipment and storage medium of a speech synthesis model. Background technique [0002] Speech synthesis models are systems that process text input and generate human-like speech. With the maturity of deep learning technology and the improvement of computer performance, deep neural network technology is widely used in the training tasks of speech synthesis models. Since neural network-based speech synthesis model training requires a large amount of text data, such data sets are usually difficult to obtain, resulting in insufficient training of neural networks and poor quality of synthesized speech in the case of limited data sets. [0003] Therefore, it is urgent to propose a training method for a speech synthesis model with good synthetic speech quality. Contents of the invention [0004] Based on this, it is necessary to provide a train...

AI Technical Summary

Problems solved by technology

Since the training of speech synthesis model based on neural network requires a large amount of text data, and such data sets are usually difficult to obtain, in the case of limited data sets, the training of neural network is not sufficient, and the quality of synthesized speech is not good.

Images