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

Abstract

The invention provides a speech synthesis method, a model training method, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-synthesized text, inputting the to-be-synthesized text to a trained target speech synthesis model, and obtaining a target speech corresponding to the to-be-synthesized text; wherein a preset speech synthesis model is pre-trained according to a pre-training set to obtain a speech synthesis model; replacing the duration prediction network of the speech synthesis model with a target duration prediction network corresponding to the target application scene to obtain a target speech synthesis model; obtaining a target training set, wherein the target training set comprises a voice sample of a target speaker; selecting voice samples of speakers of the same kind of the target speaker from the pre-training set, and performing mask noise addition to obtain noise-added voice samples; and training the target speech synthesis model according to the target training set and the noise-added speech sample to obtain a trained target speech synthesis model. According to the invention, high-quality natural and smooth voice which is more matched with the speaking style of a specific speaker can be synthesized.

Description

technical field [0001] The present application relates to the technical field of speech synthesis, in particular to a speech synthesis method, a model training method, a device and a storage medium. Background technique [0002] Speech synthesis (speech synthesis), also known as text-to-speech (TTS), aims to convert input text into smooth and natural output voice, and is a key technology for realizing intelligent human-computer voice interaction. [0003] In the traditional speech synthesis technology, constructing a speech synthesis model of a specific speaker requires 10-20 hours of recording data of the specific speaker, and the better the quality of the recording data, the better the effect of the synthesized speech. With the diversification of application scenarios, such as mobile phone assistants, car navigation, and reproduction of the voice of relatives, each application scenario requires a large amount of recording data of its representative speaker, which is diffic...

AI Technical Summary

Problems solved by technology

With the diversification of application scenarios, such as mobile phone assistants, car navigation, relatives’ voice reproduction, etc., each application scenario requires a large amount of recording data of its representative speaker, which is difficult and expensive

However, the existing speech synthesis model based on a small amount of training data is easy to fit the noise, and the synthesized speech is seriously mechanical, not smooth enough, and far from the speaker's timbre, rhythm and other speaking styles

Images